1 Introduction

Green and low-carbon highway construction is a process that constructs highways with low pollution rates. It creates proper driving spaces and environments for the users. Artificial intelligence (AI) technologies are used to improve the construction features of smart highways. Various methods are used to design infrastructure for highways [1]. A sustainability-oriented maintenance management protocol based on a Q-learning algorithm is used for the construction process [2]. The management protocol provides relevant strategies to understand the exact need for highways. The management protocols construct the infrastructure to minimize the carbon emission rate on the environment [3]. The maintenance functions and features are evaluated to produce optimal information for the low-carbon highway construction process. It also reduces the complexity ratio in the construction process [4]. A spatial–temporal mapping technique is used for green and low-carbon highway construction systems. A deep learning (DL) algorithm is implemented in the technique to track the areas for highway construction. The mapping technique decreases the biodiversity ratio via green highways. The mapping technique evaluates the satellite images and produces feasible data for the construction process [5, 6].

Computing techniques are commonly used for problem-solving issues in the green highway construction process. Computing techniques provide feasible requirements to improve the construction design of highways [7]. A green highway construction based on computing technique is used for construction systems. The highway construction technique evaluates the sensitive areas, environmental aspects, and maps for the designing process [8]. The exact requirement for green highway construction minimizes the latency in the identification process. It also provides safety management services and functions during highway construction [9]. It analyzes the requirements to construct highways that provide effective services to the users. The required constructional characteristics are evaluated for the highway construction process [10]. A green technological innovation technique is also used for green highway construction systems. A computing strategy is used in the technique to capture the regional aspects that are relevant to the construction process. The regional aspects provide feasible information to design the highways [11, 12].

Green demands are provided during every highway construction process. Green demands such as ecological factors, greenhouse gas emission range, low-carbon emission rate, and structural aspects of roads are evaluated [13]. The necessary green demands are analyzed to produce relevant data for the highway construction process. Green demands are mostly analyzed for smart highway construction systems [14]. A deep neural network (DNN)-based construction technique is used for the smart highway designing process. The DNN algorithm understands the necessary aspects that create effective highway designs for the users [15]. The DNN algorithm uses an analytical analysis method to analyze the green demands which reduces the severity range in the construction process [16]. The DNN algorithm also analyzes the necessity of the demands and eliminates unwanted demands during the highway construction process [17]. The actual carbon emission range on the environment is identified to produce optimal information for the designing phase. The green demands are mostly used to minimize the emission ratio in highway construction systems [18].

Using information from the “La Abundancia Florencia” case study, this research aims to examine the way various models for low-carbon highway construction perform. Optimizing smart highway infrastructure design is the major goal, so evaluating these models helps to meet the effectiveness of meeting eco-demands and low-carbon emissions. The study aims to find the best ways to balance infrastructure growth with environmental concerns by analyzing and comparing different models.

1.1 Research Novelty

The critical requirement to find long-term solutions to infrastructure problems that are compatible with environmentally friendly and low-carbon emission targets essentially motivates this research. Conventional approaches to highway building frequently produce more waste and pollution than necessary because they do not adhere to these environmental laws. The goal of this project is to improve highway design by reducing demand detection and evaluation time and increasing satisfaction and a recommendation through the integration of advanced algorithms like fuzzy control systems and AI. Both environmental concerns and the promotion of rational, cost-effective infrastructure development are addressed by this PCFRS strategy.

1.2 Contributions

  1. (i)

    To introduce a pollution control-facilitated recommendation system (PCFRS) specifically for green and eco-friendly highway construction, incorporating multiple considerations and fuzzy-aided analysis.

  2. (ii)

    To identify the relationship between user demand and eco-friendly demand satisfaction factors within the proposed system, enhancing highway infrastructure recommendations.

  3. (iii)

    To provide a wide data-based analysis that correlates the derivations and descriptions, and strengthening the proposed system efficacy in promoting pollution-free environments and driving spaces.

  4. (iv)

    To develop a sustainable environment by optimizing design and promoting green environments across highway lanes, addressing the challenges for eco-conscious infrastructure.

The manuscript is organized as follows. Section 2 describes the materials and methods and implements the fuzzy control algorithm, Sect. 3 presents the results with their descriptions. Section 4 discusses the results in the light of similar studies, followed by conclusion in Sect. 5.

1.3 Related Works

Rahman et al. [19] developed a renewable energy re-distribution using the Internet of things (IoT) for green highway management. Both low and high sensing are used for data aggregation. The developed model is widely used for data exchange and analytics processes. It provides a cost-effective service to the users that minimize the latency ratio in the computation process. The developed model enhances the energy efficiency range of the sensors.

For roadway optimization, Cao et al. [20] presented a smart multi-objective framework. The optimization process's critical elements are examined using a Bayesian optimization random forest (BO-RF) technique. The factors that impact the systems' concrete performance are predicted. An analysis of the precise mapping connection between services and vehicles is carried out by the suggested framework.

For optimal control of systems for reconstruction and maintenance, Bazhanov et al. [21] presented a methodology. Finding the vehicles' spatial and temporal characteristics is the approach's primary goal. Highway building and reconstruction plans mostly make use of it. The presented method generates the required rational interval for users to carry out activities. It expands the systems' practicality and reliability.

Hu et al. [22] designed a new investigation technique for vehicle driving on multi-lane highways. The actual goal of the technique is to improve the wind energy harvesting devices on the highway. It is mostly used to construct a simulation model which is implemented for running vehicles. The designed technique minimizes the latency in providing services to the vehicles. The designed technique improves the overall airflow distribution on the highway.

A photocatalytic method to increase roadway hydrogen production was suggested by Cui et al. [23]. The strategy’s true objective is to improve the ultrathin carbon bridges used on roadways. To test how the various vehicles' carbon layer nanosheets interact with one another, an ultrasonic assembling method is employed. The suggested method greatly expands the systems' potential for energy efficiency.

Salisbury et al. [24] developed a long-term tree survival method in highway rights-of-way (ROW). The developed method is mainly used to evaluate the number of tree ratio in urban areas. The developed method is used as a multi-decade research technique that analyzes the tree survival range in an urban environment. Wireless sensors are implemented to collect the necessary data for the prediction method.

Yu et al. [25] designed a new construction for highways to improve the energy storage performance of the systems. The designed structure detects the hybrid ion which causes damage to the highway environment. It enables superior energy storage that reduces the computational cost of performing tasks for the systems. The designed model improves the performance and feasibility range of ion storage.

Dong et al. [26] proposed a carbon emission model for vehicles on highways. It is a theoretical carbon emission model to evaluate the emission range of the vehicles. The exact driving behaviors of the vehicles are calculated based on the base station (BS) on the highways. The proposed model increases the accuracy of carbon emissions of the vehicles. The proposed model provides proper routing for low-carbon transportation.

Iqbal et al. [27] developed a new risk assessment using a statistical analysis for highways. It is an assessment protocol that minimizes the errors that occur on highways. The storm characteristics such as cumulative flow and vehicle volumes determine the new recommendations. Highway characteristics are also calculated for risks on highways. The developed model increases the accuracy of risk assessment which enhances the runoff volumes of highways.

Feng et al. [28] designed a multi-attractive evaluation model for country-level highways in urbanization. The designed model uses a game combination weighting method (GCWM) which analyzes the weight indexes and patterns of the vehicles. The GCWN method detects the anonymous objects present on roadsides. The designed model provides a proper rural transportation routing procedure for the vehicles.

Shoaib et al. [29] introduced a new assessment framework using a fuzzy algorithm for highways. An exploratory factor analysis (EFA) is implemented in the framework to evaluate the sustainable characteristics of the vehicles. The EFA method minimizes both the time and energy consumption ratio in the computation process. It is also used for the decision-making process that enhances the efficiency ratio of the systems. The introduced framework improves the robustness and feasibility range of the systems.

Gao et al. [30] proposed a cross-section optimization for highway alignment (COHA). The main aim of the model is to reduce the construction cost ratio of the systems. The proposed model uses a stochastic dominance (SD) theory to align the highway elements for the construction process. The proposed model is also used to reduce the carbon dioxide emission ratio on highways.

Jia et al. [31] developed a new road construction method for highways. The developed method mostly uses remote sensing images for data classification and prediction processes. Both spatial and temporal features of the highways are calculated to create an impact on the construction process. The developed method enhances the overall performance and significance ratio of highway construction systems.

Chen et al. [32] introduced a gain-scheduled state-feedback technique and a fuzzy system for controlling the linear parameter-varying (LPV) systems. To expedite this process, a fuzzy control system further generates a mixed signal with the main controller signal. The model produced good efficiency and performance.

He et al. [33] proposed an autoregressive neural network model-assisted non-linear autoregressive model on initial training samples to predict anomalies in residuals in the fitted model. The predicted anomalies are clustered using fuzzy c-means clustering. For every out-of-the-ordinary occurrence, statistical anomaly detection gives the corresponding change in mean and variance.

Sabir et al. [34] presented a combined approach for numerical second-order prediction differential models using artificial neural network and optimization using genetic algorithm and sequential quadratic programming (ANN–GA–SQP). Their research model focused on differential operator models and evaluated the precision, proficiency level, and consistency check. From their result, the model demonstrated a minimal mean square error (MSE) and achieved near optimal result.

Umar et al. [35] applied feed-forward ANN model for predicting human immunodeficiency virus (HIV) optimized using particle swarm optimization (PSO) in medical applications. Their interior point method (IPM) developed the fitness function for T cells. The accuracy of their results has been confirmed by statistical metrics and validation against established numerical processes.

Wang et al. [36] presented numerical solutions for the linear and non-linear model using Gudermannian neural networks (GNNs) along with GA and interior point algorithm (IPA). Their boundary conditions were designed and optimized for solving differential systems. Their result performance was evaluated for competence, accuracy, and proficiency. The model computational performance with error measure was illustrated.

Lavín-Delgado et al. [37] proposed a robot manipulator with a fractional controller based on derivatives and Riemann integral. Their performance is optimized using swarm intelligence algorithm for predicting the reference trajectory track. Their results demonstrated the minimal MSE under different operating conditions.

Alqhtani et al. [38] applied the stochastic model with conjugate gradient neural networks for studying malaria and the corresponding medication. The capability and knacks of the Runge–Kutta solver was developed to work under different conditions with target datasets for varying scenarios. Their research study obtained optimal result in the accurate prediction of the disease with preciseness, along with reliable and consistent results.

The discussion above relies on the conventional eco-friendly factors for the design and development of highway infrastructures. Depending on the development and progression toward green energy utilization, the alignment and modifications are less recommendable. Such processes fail the cost-effectiveness feature requiring high modifications. To prevent such interpreting alignments, this article introduced a recommendation system with diverse feature assessments across various environmental factors. This reduces the chances of modification and adapting to the modern construction features across various eco-friendly amendments.

2 Materials and Methods

Sustainable and low-carbon highway constructions are the focus of the study's recommendations, and were based on a pollution control-assisted system. To improve the decision-making procedure for smart highway constructions, the study’s design concentrated on employing fuzzy control algorithms and AI. Using a systematic manner, the technique evaluated different infrastructure models based on user expectations, eco-friendly requirements, and satisfaction variables.

The data sample selection included a case study of road construction “La Abundancia Florencia” from [39] which provided the data used in the study. Constraints pertaining to green energy consumption and demand variables informed the selection of particular models of range from model 1, model 2, model 3, and model 4. To get a good cross section of ideas for sustainable highway building, we used a random sampling technique. Besides, the model’s efficacy and drawbacks were analyzed under the different road lengths (1 km to 15 km) and emission rates (100 to 1100 kg CO2/km).

Information about CO2 emissions, user needs, satisfaction criteria, and environmentally friendly driving requirements were gathered during the data collection procedures. The interaction between demand identification, satisfaction parameters, and environmental considerations was analyzed using the dataset from the selected models. Obtaining pertinent information to input into the recommendation system was the primary emphasis.

Data analysis incorporated artificial intelligence and fuzzy control algorithms to determine the best eco-friendly roadway design and recommendations. The investigation examined user needs, satisfaction, and eco-friendly criteria. Fuzzy decision-making iterations were used to improve smart highway infrastructure development efficiency and cost.

2.1 Data Description

The data from [39] was utilized in this article from the “La Abundancia Florencia” case study of road construction. This article provides different models for low-carbon highway construction. From the different models, we select four models with the following constraints for green energy and demand factor as per the recommendations. The recommendations are provided as per the drivers and public opinion acquired. In Fig. 1, the four models and their specs are represented.

Fig. 1
figure 1

Specifications of the four models proposed for low-carbon highway construction. Depending on the constraints above, the eco-friendly elements are used for highway construction. In this case, the demands before construction (improvements) and its achievements (for satisfaction) are estimated using CO2 emissions. This serves as the computing factor for demand and satisfaction analyzed using the fuzzy process. Based on these features, the recommendations are provided. For example, though models 3 and 4 are the same, the recommendation (for improvement) is optimal in projecting model 4 (refer to Fig. 1).

Full size image

2.2 Pollution Control-Facilitated Recommendation System (PCFRS)

The prime requirement for constructing green and low-carbon highway infrastructure for maintaining their mutual relationship is achieved using eco-demands and low-carbon emissions to reduce the decision-making for the best smart highway infrastructure with less cost overhead. The research article presents study data and suggests a recommendation system for low-carbon highway development that is aided by pollution control. To improve highway design while taking environmental considerations and government policies into account, it discusses different models, their specifications, and algorithms. Consequently, rather than offering suggestions for ideas or concepts, it concentrates on delivering study results and recommending a workable approach.

Every country has different government policies and environmental departments to develop and improve the demands and relationship factors across various infrastructures. In this system, eco-friendly driving demands and low-carbon emissions are the main requirements for designing such highways based on demand and satisfaction factors. This two-factor relationship is verified using fuzzy control for gaining optimal design for best infrastructure recommendations. The green demands are satisfied based on government demand and requirement factors of any country to improve the relationship between the demand factor and satisfaction factor. The proposed system is diagrammatically portrayed in Fig. 2.

Fig. 2
figure 2

Diagrammatic representation of the proposed system

Full size image

This PCFR system focuses on the environmental departments and governance agencies’ policies for satisfying eco-demands and low-carbon emissions for constructing smart highways through AI and fuzzy control algorithms for preventing the cost overhead and failures. Pollution control-facilitated recommendation system (PCFRS) defines a system that is designed for highway infrastructure construction and concentrates on eco-friendly driving demands along with low-carbon emissions. Several factors might cause error propagation in the PCFRS algorithms suggested in this study, which try to estimate solutions for environmentally friendly highway construction. There are a number of factors that could cause problems, including faulty input data, incorrect assumptions in the models, complicated algorithms that cause iterative errors, parameters that are too sensitive, and ever-changing policy and environmental situations. Despite the useful insights they provide, fixing these error propagation sources is essential for optimal highway infrastructure design approaches to be reliable and accurate.

These green demands as formulated by the present governing agencies/environmental departments are used for checking the demands and relationship factors of different infrastructures. The variations in the demand factor and satisfaction factor are analyzed using a fuzzy control algorithm that relies on environmental departments/governing agencies to improve the design of such highways with advanced AI. The demand and relationship factor is observed, crisp input from the government policies based on the demand/relationship factor is verified, and the maximum possible combinations of the satisfaction factor lead to economic development, if the smart highways are constructed to promote green environments are optimal across different highway lanes. However, the demand factor and satisfaction factor are vice versa, so better infrastructure recommendations are provided to design such a highway.

2.2.1 Fuzzy Process

This fuzzy algorithm is an approach used to validate the factors based on “degrees of truths” observed from the instance with the usual 0 and 1 conditions. In AI systems, fuzzy control is aided by copying human reasoning and cognition. The fuzzy decision includes 0 and 1 for the maximum possible combinations, but promotes green environments across various highway lanes. A schematic representation of the fuzzy process is given in Fig. 3.

Fig. 3
figure 3

Schematic representation of the fuzzy process

Full size image

The fuzzy crisp inputs are handled as DFxy (demand) and relationship (ϕP). These two factors’ maximum combinations (between 0 and 1) are used for deciding over the satisfaction (achieved) or recommendation (provided) for validating the outputs x and y for low-carbon and eco-friendly assistance using the layered combination of fuzzy with its continuity, and the recommendations are pursued. In the different combinations, the output of DF, ϕF, recommends the decision for the available infrastructures (Fig. 3). This fuzzy algorithm first takes the demand factor and relationship factor as input for making better decisions. Each country has its eco-friendly demands and low-carbon emissions across various infrastructures for designing smart highways. Based on the environmental departments/governance agencies, if the fuzzy algorithm outputs 0, the maximum possible combinations of the satisfaction factor are achieved and then optimal designs are planned to construct a highway. Instead, if the fuzzy control output is 1, the variations are identified in that particular infrastructure and then provide recommendations to change demands and requirements based on the government policies. This process is performed until the maximum satisfaction factor is achieved. Each fuzzy decision finds the best-fit recommendations and maximum satisfaction of the demand factor. The green demands for highway construction depend on the eco-demands, and low-carbon emission is computed as

$${HWC}_{xy}\left({\Delta }_{infra}+1\right)=P\left({EvD}_{p}\left({\Delta }_{infra}\right)\times {GvA}_{p}\left({\Delta }_{infra}\right)\right) +Q\left({DF}_{xy}\left({\Delta }_{infra}\right)-{SF}_{xy}\left({\Delta }_{infra}\right)\right)+R.$$
(1)

In Eq. (1), the variable \({HWC}_{xy}\left({\Delta }_{infra}+1\right)\) represents the high construction with eco-demands \(x\) and low-carbon emissions \(y\) across various infrastructures \({\Delta }_{infra}\) for designing such a highway, where \({EvD}_{p}\left({\Delta }_{infra}\right)\) and \({GvA}_{p}\left({\Delta }_{infra}\right)\) denote environmental department and governance agency policies for \(x\) and \(y\), and \(Q\) are the two random variables between \(\left(0, 1\right)\) for variation analysis and \(R\) is infrastructure recommendation. \({DF}_{xy}\left({\Delta }_{infra}\right)\) and \({SF}_{xy}\left({\Delta }_{infra}\right)\) are the demand factor and satisfaction factor of infrastructure. The decision for a new highway construction infrastructure handling is expressed as

$${\Delta }_{infra}\left({EvD}_{p}\times {GvA}_{p}\right)=\sum_{i=1}^{N}\left(1+\frac{x\left({\Delta }_{infra}\right)+y\left({\Delta }_{infra}\right)}{{HWC}_{xy}\left({\Delta }_{infra}+1\right)}\right).$$
(2)

Equation (2) computes the properly planned highway construction infrastructures based on endorsed green and low-carbon handling for pollution-free environments and expanded driving spaces through fuzzy decisions with government policies. The \(\sum_{i=1}^{N}\left(1+\frac{x\left({\Delta }_{infra}\right)+y\left({\Delta }_{infra}\right)}{{HWC}_{xy}\left({\Delta }_{infra}+1\right)}\right)\) summation row ranges from \(i=1 to N\), and defines the total number of terms in the summation. The satisfaction factor is \({SF}_{xy}=1\) outputs in less relationship and demand factor in that infrastructure and identifying the variations, hence the least possible combinations is achieved to design highway with proper infrastructure recommendations. In this process, the variable \(n\) indicates the total number of eco-demands in each infrastructure and \(t\) indicates different periods. Therefore, smart highway construction with high cost-effectiveness is constantly performed with proper infrastructure recommendations. The least possible satisfaction is expressed by \({SF}_{xy}\in \left[\text{0,1}\right]\) and the demand and satisfaction factor relationship is output in a varying manner. Here,\( {SF}_{xy}=1\) is addressed at any period, then fuzzy decision outputs in the least possible combination of the satisfaction factor. This last possible combination is addressed in any infrastructure that leads to high pollution and small driving space. The environmental departments' and government agencies' policies are jointly balanced using the proposed system to maximize the satisfaction factor. The satisfaction estimation decision using the fuzzy is presented in Fig. 4.

Fig. 4
figure 4

Satisfaction estimation decision

Full size image

The highway construction process identifies \(x\) and \(y\) based on emissions and the user reviews consistently. Based on \(S{F}_{xy}=1(max)\), further recommendations are pursued. The recommendations are positive for expanding \({\Delta }_{infra}\) for improving eco-friendly objectives. The failing condition is redirected to compute \({\phi }_{F}\) for which further \(\left(x,y\right)\) and \(\left(P,Q\right)\) estimations are pursued. The extracted data is decisive until \(S{F}_{xy}\) is improved compared to the previous validation case (Refer to Fig. 4).

2.2.2 Recommendation Process

In this proposed recommendation system for smart highway construction, the satisfaction factor is maximized by verifying the demands and relationship factors across various infrastructures in any country. The demand and satisfaction factors are verified through a fuzzy control algorithm to provide the best recommendation for designing such a highway. The pollution control recommendation system mainly focuses on eco-demands and low-carbon emission infrastructure for optimal design. The less cost overhead design also planned by the government due to increasing population growth and cities is achieved as per Eq. (1). The possibility of maximum satisfaction factor achieved by any infrastructure includes recommendations to increase smart highways. Based on the current eco-demands and low-carbon emissions, the cost-effective for constructing smart highways is expressed as

$${\complement }_{ef}=\frac{\left({HW}_{1}+{HW}_{2}+\dots +{HW}_{n}\right)/3-{L}^{DF}}{{BF}_{R}},$$
(3)

where \({\complement }_{ef}\) is the planning of cost-effective smart highway construction design and the variable \(\left({HW}_{1}+{HW}_{2}+\dots +{HW}_{n}\right)\) denotes the number of highways in a particular country; \({L}^{DF}\) is the least demand factor and \({BF}_{R}\) is the best-fit recommendation for highway construction design.

\({L}^{DF}\) can be expressed as:

$${L}^{DF}=\frac{Max\left({L}^{DF}\right)-Min\left({L}^{DF}\right)}{1-{\exists c}^{{\Delta }_{infra}}},$$
(4)

where \(Max\left({L}^{DF}\right)\) and \(Min\left({L}^{DF}\right)\) are the maximum and minimum least demand factors observed from the infrastructure using fuzzy decision; \({\exists c}^{{\Delta }_{infra}}\) is the low pollution infrastructure for highway construction. This is expressed as:

$${\exists c}^{{\Delta }_{infra}}=\frac{{HWC}_{xy}\left({\Delta }_{infra}+1\right)\left(Max\left({L}^{DF}\right)-Min\left({L}^{DF}\right)\right)}{\frac{n}{2}\left(t-2{EvD}_{p}+{GvA}_{p}\right){L}^{DF}},$$
(5)

where from the varying demand factors and relationships at different infrastructures, the best design is planned and can be expressed as follows:

$${BD}_{xy}=\left(\frac{n}{2}-t\right){\left({\Delta }_{infra}-{\exists c}^{{\Delta }_{infra}}\right)}^{2}.$$
(6)

The least possible combinations of the satisfaction factor identify the variations in demand and relationship factors. The low-cost overhead and less carbon emission-identified infrastructures are used for constructing the highway; it is the best output to balance a green environment and driving spaces for designing smart highways. Hence, this condition \(\frac{\left({HW}_{1}+{HW}_{2}+\dots +{HW}_{n}\right)/3-{L}^{DF}}{{BF}_{R}}\) exceeds, and then a fuzzy control algorithm is used for the best design. The least possible combinations-based infrastructures maximize the demanding factor and deface the eco-demands and low-carbon emissions across various infrastructures. The recommendation process is illustrated in Fig. 5.

Fig. 5
figure 5

Recommendation process illustrations

Full size image

The \({L}^{DF}\) analysis is performed by distinguishing \(t\) for analyzing different models. These models are unanimously validated for \(B{F}_{R}\) and low \({L}^{DF}\) under recurrent fuzzy processes. If the relationship factor coincides with \(\exists {C}^{{\Delta }_{Infra}}\) for the varying \({\phi }_{F}\) and \({D}_{F}\), then the design is recommended. Therefore, \(\left(x,y\right) \forall (P,Q)\) are the testing (trial)-related \({\complement }_{ef}\) factors for the alternate designs (Fig. 5). The green environment and low-carbon emission handling are the best solution identified using fuzzy decision. The best solution is achieved by mitigating the least possible combinations of the satisfaction factor through a fuzzy control algorithm. Considering these green demands formulated, the environmental department/governance agencies are aided in verifying accurate demand and relationship factors. In this proposed system, the least possible combinations are identified and analyzed for reducing overhead and providing better recommendations, which vary based on the condition as per Eq. (1). As per this proposed system, the number of optimal designs for highway construction is computed with the first demand, and a relationship factor is identified to validate the satisfaction factor. In addition, the fuzzy decision is used to achieve the maximum possible combinations of the satisfaction factor and provide the best recommendations with the following cases.

2.2.3 Optimal Design Using Fuzzy Validation Cases

The demand and low-carbon emission are verified in that particular infrastructure is used to design the best highway construction as follows.

Case 1: demand = 0, satisfaction = 1.

Solution 1: If the demand is 0, then the governance policies are formulated to design the highway with high carbon emission, less eco-demands, high cost, etc. The highway construction is designed to augment the country's transportation and thereby satisfy the people’s demands and requirements. The number of cities is counted and the recommendation provides for new construction because it increases space complexity and time complexity. The number of highways constructed is calculated randomly. Across various infrastructures, the best highway construction is designed for a pollution-free environment and low-carbon emissions. The maximum satisfaction factor with zero demand is expressed as

$$Q={HW}_{n}\times {\exists c}^{{\Delta }_{infra}}+{HW}_{n}\times t+{HW}_{n}\times {SF}_{xy.}$$
(7)

The output of the above case is presented in Fig. 6.

Fig. 6
figure 6

Case 1 output analysis

Full size image

The \(P,Q\) impact over the varying \({\phi }_{F}\) and \(DF\) are analyzed in Fig. 6. The fuzzy decision process relies on \(\exists {C}^{{\Delta }_{infra}} \in HW\) such that demand is at most satisfied. As the practical situations (constraints) presented in Fig. 1 are mended by distinguishable agency and government policies, \(DF\) varies. This directly impacts \({\phi }_{F},\) for which a similar converging point is expected. Using the recommendation and satisfaction for the varying \(\left(x,y\right),\) the above case is verified.

Case 2: demand = 1, satisfaction = 0.

Solution 2: In this constraint, the demand is given by the government. Based on the governance policies, the highway construction design is planned at a low cost. The minimum cost-effectiveness noticed in that condition is expressed as

$${\complement }_{{ef}_{min}}=\frac{{\exists c}^{{\Delta }_{infra}}}{{HW}_{n}}\sum_{t=1}^{n}\sum_{x=1}^{n}\sum\nolimits_{y=1}^{N}{\left({P}_{xy}+{Q}_{xy}\right)}^{2},$$
(8)

where \(t,x,y\) all iterate from 1 to n. Post the demands are addressed, the satisfaction factor is verified using fuzzy decision; the fuzzy algorithm with the demand and relationship factor is served as input. \(t\) is the time to construct the highway. A less cost-effective design is planned. If the current demands and relationship are verified, then the best recommendation is made to minimize the cost overhead and time complexity. The case 2 outputs are analyzed in Fig. 7.

Fig. 7
figure 7

Case 2 output analysis

Full size image

\(P\) and \(Q\) influencing factors have inverse impact over \(DF\) and \({\phi }_{F}\) such that the decision is revisited. Considering \(S{F}_{xy}=1\) for deciding \({L}^{DF}\) and its variants, \({C}_{e{f}_{min}}\) is satisfied. The consecutive design requires cost and constraint satisfaction for \(B{F}_{R}\). This is utilized for different \({Q}_{xy}\) conditions across various \(P\) and \(Q\). Therefore, case 2 is less reliable compared to case 1 (Fig. 7).

Case 3: demand = 1, satisfaction = 1.

Solution 3: The highway construction designed with government policies is the best output. The probability of high carbon emission is identified based on industry wastage leakage, high traffic, etc. Therefore, the low-carbon emission infrastructure is best suited for highway construction. From the minimum possibilities, the demand and relationship factor across various infrastructures is continuously verified to achieve the satisfaction factor. The recommendation for the best highway design \(R\left(BD\right)\) is expressed as:

$$R\left(BD\right)=\frac{{\left({HW}_{n}\right)}_{xy}}{\sum_{t=1}^{n}{\left({EvD}_{xy}+{GvA}_{xy}\right)}_{{\Delta }_{infra}}}.$$
(9)

In this analysis, the recommendations will be provided for all the infrastructures to construct highways based on eco-demands and low-carbon emissions. The case 3 analysis is presented in Fig. 8.

Fig. 8
figure 8

Case 3 analysis

Full size image

The final case is the maximization of \(DF\) and \({\phi }_{F}\) by satisfying the \(x\) and \(y\) constraints. In this process, the fuzzy control optimizes the changes in \(S{F}_{xy}=1\) such that \(0\le P\le 1\) and \(0\le Q\le 1\) are balanced using different decisions. The decisions are planned to satisfy \({C}_{ef}\) and \({L}^{DF}\) based on \(B{D}_{xy}\) such that case 3 is satisfied in any \(t\) (Fig. 8). The demand and relationship factor is also verified for reducing the failures. The best solution is made based on the demand factor and satisfaction factor with the \(x\) and \(y\) variations are computed as

$${DF}_{xy}={\left({HW}_{n}\right)}_{xy}\left(1-{\exists c}^{{\Delta }_{infra}}\right){\left({EvD}_{xy}+{GvA}_{xy}\right)}_{{\Delta }_{infra}.t},$$
(10)

and

$${SF}_{xy}={DF}_{xy}+{\varnothing F}_{xy}\left(1-F\right){\Delta }_{infra}.t,$$
(11)

where \(\varnothing F\) denotes the relationship factor; therefore, the best recommendation for highway construction is made for each infrastructure for \(x\) and \(y\). The best-fit design formulated \(EvD/GvA\) is computed as

$${BFD}_{EvD/GvA}=\left\{\begin{array}{c}{DF}_{xy}+{\varnothing F}_{xy}\left({HW}_{n}+R\left(BD\right)\right)-F, {\Delta }_{infra}\ge t\\ {\complement }_{{ef}_{min}}+\left(1-\frac{{DF}_{xy}+{\varnothing F}_{xy}}{{SF}_{xy}}\right), {\Delta }_{infra}<t\end{array}.\right.$$
(12)

Equation (12) computes the maximum possible combinations of the satisfaction factor with low-carbon emission and eco-demands to improve the aim of such highway constructions. The low-cost overhead and best infrastructure identified places suitable for highway construction. Based on the condition, the high demand factor and high satisfaction factor identified infrastructure that is most suitable for highway construction. In this system, the fuzzy decision is used to make optimal designs for constructing the highway with government policies. Therefore, the failure and time and space complexity are less. The cost-effectiveness and other associated constraints as in Fig. 1 for the four models evaluated by this proposal are analyzed in Table 1.

Table 1 Model’s efficiency analysis
Full size table

For the models considered in Fig. 1, the efficiency factors (i.e.,)\( D{F}_{xy}, {L}^{DF}, {C}_{e{f}_{min}}, S{F}_{xy}\) and \(R\left(BD\right)\) are validated in Table 1. \(R(BD)\) is influenced by \({L}^{DF}\) (min and max) for which \({C}_{e{f}_{min}}\) is either true or false. The fuzzy differentiation is optimal in matching if DF and \(S{F}_{xy}\) are satisfied using \({\phi }_{F}\). In this case, the validity of the deciding factors is used for model recommendation across various \(t\). Therefore, each model is foreseen as an advancement of the previous with maximum improvement.

3 Result Analysis

In this subsection, the analysis of the following metrics is presented with a model-based description: satisfaction factor analysis, recommendation ratio, demand identification, analysis rate, and time requirement. The four models from the data description subsection are used in this metric analysis for a detailed discussion. Besides, the model’s efficacy and drawbacks are analyzed under the different road lengths (1 km to 15 km) and emission rates (100–1100 kg CO2/km). The cross-validation involves running k-fold cross-validation multiple times with different random splits and estimate the model performance in terms of five folds. The model is trained using four folds and tested on the remaining one fold. This process is repeated five times, with each fold serving as the test set exactly once. The cross-validation involves running k-fold cross-validation multiple times with different random splits and estimate the model performance in terms of five folds. Along with this, sensitivity analysis is used to analyze the critical parameters for ensuring the reliability of the model.

3.1 Satisfaction Factor Analysis

The satisfaction factor analysis is high in the proposed system compared to the other factors (Refer to Fig. 9). In this system, the eco-demands and low-carbon emission is verified for identifying the demand factor. In case 1, the demand factor is 1, and the satisfaction factor is 0; therefore, the recommendation for highway construction is made based on governance policies [as in Eq. (1)], then \(SF\times DF\) and \(DF\times t\) are suitable infrastructures identified. Based on this analysis, \(SF\) is determined. The proposed system meets the eco-demands successfully and ensures low-carbon emissions, resulting in the best satisfaction factor. Optimization of highway construction recommendations is achieved through the employment of a fuzzy control algorithm-governed mix of demand and satisfaction parameters. The concept guarantees eco-friendly infrastructure by reducing demand identification and variability and achieved. Based on the results shown in Fig. 9, this model is clearly the best option for environmentally conscious highway building. The maximum possible combinations of the satisfaction factor due to less demand identification and low-carbon emission for highway construction are considered. This consideration requires high satisfaction factor analysis, preventing high pollution environment and variations. Hence, the green and low-carbon highway construction is administered as derived in Eq. (5) with \({\exists c}^{{\Delta }_{infra}}\) computation. The first highway construction is made across various infrastructures and verified, for which \(\frac{{HWC}_{xy}\left({\Delta }_{infra}+1\right)\left(Max\left({L}^{DF}\right)-Min\left({L}^{DF}\right)\right)}{\frac{n}{2}\left(t-2{EvD}_{p}+{GvA}_{p}\right){L}^{DF}}\) alone is validated. In this condition, the change in current eco-demands and its existing \(SF>t\) is analyzed for variation analysis. This process helps in preventing additional demand identification as mentioned above. Therefore, for \(SF>t\), the demand and relationship is verified, improving the decisions, and the satisfaction factor under the fuzzy control algorithm is high. In the proposed system, the analysis relies on \(\left({\Delta }_{infra}-{\exists c}^{{\Delta }_{infra}}\right)\) and hence the demand identification is considerably less. Highway building with minimal carbon emissions and maximum satisfaction factor from reduced demand identification are both taken into account and analyzed.

Fig. 9
figure 9

Satisfaction factor

Full size image

3.2 Recommendation Ratio

This proposed system achieves a high recommendation ratio for various demand factors and relationship factors as represented in Fig. 10. Hence, \(SF > t\) affects both the demand and satisfaction factors; for the recommendation rate to improve, this satisfaction component must meet three separate situations. The demand identification is alleviated based on the environmental department/governance agency's policies for optimal highway design and promoting green environments through a fuzzy control algorithm. The \(DF\) and \(\varnothing F\)-based satisfaction factor analysis is pursued, using previous and current demands and the best design for highway construction is made with less demand identification and overhead costs. Further, the satisfaction factor is used for increasing the analysis rate and time requirement beyond exceeding \(SF>t,\) and hence the recommendation is increased. In various highway constructions, the fuzzy decision is made for less demand identification as in Eq. (8). Therefore, the demand and satisfaction factors may vary depending on \(SF>t.\) This satisfaction factor has to satisfy three distinct cases for improving the recommendation rate. The first design for highway construction satisfies both demand and satisfaction factors such that infrastructure recommendation is retained. As per the retained case, the demand and requirement factors are exploited for their mutual relationship function based on \(\frac{\left({HW}_{1}+{HW}_{2}+\dots +{HW}_{n}\right)/3-{L}^{DF}}{{BF}_{R}}\) and therefore \(SF>t\) is used to satisfy green demands. Using a fuzzy control algorithm that aligns with environmental and governance procedures, the suggested system optimizes highway design while balancing the identification of demands with financial overheads. The model uses a satisfaction factor \(\varnothing F\) and a demand framework \(DF\) to boost recommendation ratios whenever the level of satisfaction factor is above a certain threshold \(SF>t\). This improves building strategies and guarantees that infrastructure proposals fulfill green criteria. The total effectiveness of recommendations is enhanced by established policies and relationship functions.

Fig. 10
figure 10

Recommendation ratio

Full size image

3.3 Demand Identification

The proposed system satisfies less demand identification and analysis time, as it does not provide continuous recommendations for assisted applications. The varying demand and relationship factor is analyzed to identify accurate demands and requirements of the government. The high demand identification addressed in this dense application is difficult, to overcome this issue using the best suitable recommendations. The three distinct cases are analyzed without augmenting the demand identification and analysis time. Similarly, \(\left(t+1\right)\)-based highway construction requires demands and relationship verification without additional recommendations. The demand and requirement factors are sequentially analyzed, and verifications are performed to prevent additional demands and requirements. The demand identification is performed based on infrastructure and \(SF>t\) is defined for further recommendation to prevent high time and space complexity. This proposed system is used to handle pollution-free environments and driving spaces for highway infrastructure construction based on green demands for which the best recommendation is provided. To determine the government's precise requests and requirements, the variable demand and relationship factor is examined. It is difficult to identify the eco-demands for which the proposed system achieves less time complexity as presented in Fig. 11.

Fig. 11
figure 11

Demand identification

Full size image

4 Analysis Rate

The proposed system requires a high analysis rate compared to the other factors. Three distinct cases are pursued for satisfying less demand identification and analysis time using the fuzzy control algorithm and proposed system. First, the highway construction based on \(\left(DF, SF\right)\) for \(x\) and \(y\) is observed from the particular infrastructure without additional demand identification. With the incorporation of AI and smart computing features, the sophisticated decision systems augment the aim of such smart highway constructions and recommendations regardless of the various infrastructures, preventing time complexity and cost overhead. The pollution control-facilitated recommendation system is used for the continuous demand identification based on eco-demands and low-carbon emission. For the above-discussed cases, the analysis rate is high due to mutual relationships being verified such that green demands are satisfied. For reducing demand identification, the demand and relationship factors are verified under AI, and a fuzzy control algorithm is recurrently performed. The green demands are satisfied based on the environmental department/governing agencies for verifying the demand and requirements factors. In comparison to the other considerations, the suggested approach necessitates a high analysis rate. The verification confines the demands and requirements using a fuzzy control algorithm; thus the analysis rate is high as represented in Fig. 12.

Fig. 12
figure 12

Analysis rate

Full size image

5 Time Requirement

In Fig. 13, the time requirement is computed under artificial intelligence, and a fuzzy decision for designing such highways based on eco-friendly driving demands and low-carbon emissions is pursued across various infrastructures. The green demands are observed from the particular infrastructure for identifying demands and requirements for preventing pollution-free environments. From the demand, identification is performed for their mutual relationship such that the green demands are satisfied. The demand identification is performed using the proposed system for the condition \(\frac{Max\left({L}^{DF}\right)-Min\left({L}^{DF}\right)}{1-{\exists c}^{{\Delta }_{infra}}},\) for the maximum demand factor observation from the different infrastructures through a fuzzy algorithm to achieve a high time requirement. Based on the high satisfaction factor, the time requirement and recommendation ratio increase to prevent additional demands identification. To avoid the identification of unnecessary demands, the time required and suggestion ratio are increased in relation to the high satisfaction factor. The fuzzy decision satisfies the maximum possible combinations of the satisfaction factor for providing high recommendations for constructing highways with high time requirements. Based on the system’s analysis, model 4 appears to be the most effective model since it has the highest values for the major efficiency variables and each model is a progression of the preceding with greatest improvement.

Fig. 13
figure 13

Time requirement

Full size image

The purpose of the sensitivity analysis is to determine the impact of changing critical parameters within a predetermined range on the study’s results. Researchers can determine the model’s sensitivity to changes in characteristics like building costs, energy efficiency, carbon emissions, and demand factors by methodically modifying these variables.

The study modifies each parameter within its specified range in a methodical way and watches the research results alter. Understanding the impact of changing particular parameters on the model’s outputs is crucial for interpreting the sensitivity analysis results. The sensitivity analysis revealed that among the three factors influencing the total cost of highway construction—construction cost, carbon emissions, and energy efficiency—construction cost was the most important analyzed from this model. This helps in prioritizing the resources and focus on optimizing the most influential parameters to achieve effective results.

6 Discussion

In comparison to existing similar approaches, the proposed solution performs far better across every aspect. An increase of 10–20% is reflected in the significantly higher satisfaction factor (SF) of 0.92 compared to the usual range of 0.75–0.85. Similarly, at 0.88, the suggested ratio is much higher than the typical range of 0.70–0.80, which is around 15–20% lower. An additional notable improvement is the efficiency of demand identification, which scored 0.90 as opposed to the typical 0.70–0.80, indicating a decrease of 15–20% in needless demand identification. The incorporation of AI and smart computing is highlighted by the analysis rate, 0.85, which is 10–20% higher than the average range of 0.65–0.75. The significant increases in the other measures more than make up for the somewhat increased time requirement of 0.80 relative to the 0.65–0.75 range. In sum, these updates prove that the suggested system works as advertised, improving infrastructure planning through the use of cutting-edge algorithms to optimize highway building. The final outcome is better analysis rate, efficiency in identifying demands, satisfaction, and recommendation accuracy.

6.1 Advantage and Potential Limitation

The research integrates AI and fuzzy control techniques to improve smart highway construction efficiency and cost. It sets a sustainable infrastructure standard by prioritizing environmental sustainability.

Due to the unique nature of the case study and the models employed, the results may not be applicable to a broader context. Relying on fuzzy control techniques may add complexity and necessitate specific knowledge to execute.

Several factors might cause error propagation in the PCFRS algorithms suggested in this study, which try to estimate solutions for environmentally friendly highway construction. There are a number of factors that could cause problems, including faulty input data, incorrect assumptions in the models, complicated algorithms that cause iterative errors, parameters that are too sensitive, and ever-changing policy and environmental situations. Despite the useful insights they provide, fixing these error propagation sources is essential for optimal highway infrastructure design solutions to be reliable and accurate.

7 Conclusion

This article introduced a pollution control-facilitated recommendation system for improving the design and development of eco-friendly, low-carbon-experiencing highways. In this proposal, the satisfaction and demand factor relationships are exploited to meet user demands across various running lengths. The PCFRS is used for addressing and verifying the demand factor and satisfaction factor using government policies. Therefore, the lower cost overhead is addressed in this system such that green demands are satisfied. This system is applied to improve satisfaction factors and recommendations, thus reducing costs overhead and improving decision-making for optimal highway infrastructure using a fuzzy algorithm. The fuzzy process derives various decisions using multiple conditional combinations for improving the recommendations. In conclusion, the results demonstrated that the proposed PCFRS model efficiently addressed demand and satisfaction factor relationships, had greater recommendation ratio, improved demand identification efficiency, enhanced analysis rates, and managed time requirements for effective decision-making. These findings validate the effectiveness of PCFRS in improving the design and development of eco-friendly and low-carbon highway construction Therefore, the proposed system is designed to estimate the efficacy of different infrastructure models such that the improvements meet the eco-friendly and green environment recommendations.