Abstract
In the last years, the yield of Colombian crops has been affected by climate change. The weather variation affects the Colombian crops with the occurrence of diseases as coffee rust. To address the coffee rust control, we proposed a cloud-based platform for decision making support named AgroCloud. The coffee crop weather of 100 municipalities from upper basin of the Cauca river were monitored. This information was used to improve the disease control process. User Acceptance Test carried out with domain end users show that the platform is useful and is easily usable.
Keywords
1 Introduction
In Colombia, one of the biggest challenges is the marketing of agricultural products. The crops have increased twelve-fold compared with the crops in the last 20 years. 42.3 millions of hectares are committed to agriculture yield and 7.1 millions hectares in crops [1]. The Colombian farmers play an important role; they produce 78.8% of agricultural products and 60% are products of the basic food basket for Colombian people [2].
In the last years, the yield of Colombian crops has been affected by climate change. The increase of temperatures and rainfall variation affect the Colombian crops with the occurrence of diseases and pest invasions [3].
The rust is an example of a disease. The rust attacks to coffee crops where the weather is a key factor for its germination. The Rust disease has reduced considerably the coffee production in Colombia (by 31% on average during the epidemic years compared with 2007). These reductions have had direct impacts on the livelihoods of thousands of small holders and harvesters [4]. More than 350.000 Colombian families depend on coffee harvest for their sole income. As such, the coffee rust impacts terribly on the economic and social aspects of the main coffee-growing regions [5].
To tackle the aforementioned problem, we propose a cloud-based platform for decision making support in Colombian agriculture named AgroCloud. The study case is the coffee rust. The remainder of this paper is organized as follows: Sect. 2 presents the study case and related works; Sect. 3 the AgroCloud platform; Sect. 4 presents results and Sect. 5 conclusions and future work.
2 Background
In this section, we explained the study area and the concepts that are employed in AgroCloud.
2.1 Study Case
The study case of AgroCloud is the coffee rust. The weather conditions of the coffee rust are monitored in 100 municipalities from upper basin of the Cauca river (ubCr). The disease and the monitored area are explained next.
Coffee Rust is caused by the fungus Hemileia vastatrix, a parasite that affects the coffee leaves. Among the cultivated species, Coffea arabica is the most severely attacked. The disease causes defoliation, in the worst-case scenario (Fig. 1a), death of branches and crop losses [4]. The first symptoms are yellowish spots that appear on the underside of leaves (Fig. 1b). These spots then grow and produce uredospores with a orange colour. Chlorotic spots can be observed on the upper surface of the leaves [6, 7].
Below is described the Colombian region where the weather conditions of the coffee rust are monitored.
Monitoring the Coffee Crop Weather 100 municipalities from upper basin of the Cauca river (ubCr) are monitored by AgroCloud. ubCr is composed by four Departaments: 32% Cauca, 47% Valle of Cauca, 13% Risaralda and 8% Quindio. The total area of ubCr is represented by 23.000 Km2 with a population of 7.122.518 people. The main crops seeded in ubCr is the coffeeFootnote 1. Figure 2 shows the 100 municipalities on upper basin of the Cauca river.
2.2 Decision Support Systems
One important concept to understand AgroCloud are the Decision Support Systems (DSS). Scott et al. [8] a recognized researchers in DSSs field define them as systems that combine individual intellectual resources and the capabilities of a computer to improve the decisions quality.
From agriculture, a DSS is a mechanism that collects, organizes, and integrates all types of information required for producing a crop; The first step consists in the analysis and interpretation of the information; subsequently the analysis is used to recommend the most appropriate action choices [9]. Expert knowledge is a key element of DSS and it is used to assist producers with both daily operational and long-range strategic decisions [10].
In this work, a cloud-based platform for decision making support in Colombian agriculture is proposed. The coffee rust was the disease taken as study case.
2.3 Related Works
Although our proposal is focused in a decision support system for chemical control in crops with coffee rust, we consider important describe the works that address the coffee rust detection from computer science, since that task is the starting point for disease control. Also, works that propose the use of DSS in diseases crops.
Coffee Rust Detection within computer science is addressed from data mining. Colombian and Brazilian researchers have in recent times attempted to detect the coffee rust through Decision Trees (DT), K Nearest Neighbor (K-NN), Bayesian Networks (BN), Support Vector Machines (SVM), Artificial Neural Networks (ANN) and Ensemble Methods. Table 1 shows a summary of the related works for coffee rust detection.
In Colombian coffee crops, two datasets were used. The first one was collected trimonthly for 18 plots, closest to weather station at the Technical Farm (Naranjos) of the Supracafé, in Cajibio, Cauca, Colombia (21\(^{\circ }35^\prime \)08\(^{\prime \prime }\) N, 76\(^{\circ }32^\prime \)53\(^{\prime \prime }\)W), during 3 years (2011–2013). The dataset contains variables related with Weather conditions, Physic crop properties, and crop management [12]. The second dataset was obtained from Jazmín Village which is a coffee growing area sowing with Caturra variety in 45 farms approximately, monitored by Cenicafé and located in Santa Rosa de Cabal, Colombia (4\(^{\circ }\)55’00”N, 75\(^{\circ }\)38’0”W). The dataset contains samples for six daily meteorological attributes around 26/02/1986 and 15/12/1988 [7].
From Brazilian coffee crops, a dataset was built with information of the experimental farm Procafé (South latitude 21\(^{\circ }34^\prime \)00\(^{\prime \prime }\) longitude West 45\(^{\circ }24^\prime \)22\(^{\prime \prime }\) and altitude 940 m) located in Varginha, Minas Gerais, during the years 1998 – 2006. This dataset contains physic crop properties and weather conditions [18].
The main problem of the related works mentioned above is the low number of samples of Incidence Rate of Rust; if the available examples are few, the dataset does not represent a sample trustworthy of the population, then the data mining algorithms will be not inaccurate [7, 11].
Decision Support Systems for Crops Several DSSs for crops have been developed. We reviewed works from 2012 until present year. DSSs for control of diseases in crops of potato, tomatoes, grapes and wheat have been built, while DSSs for crops of citrus, soybean, sorghum, rapeseed, cardoon and sugarcane are focused in crop management. Table 2 presents a brief summary of related works of DSS in crops.
Although numerous works propose DSSs for control of diseases and crops management, at the present time, these are not focused in coffee crops to control the rust. In the next section we explain AgroCloud: a cloud-based platform for decision making support for control of coffee rust.
3 AgroCloud Architecture
3.1 Conceptual Diagram
The DSS conceptual diagram for the detection and control of coffee rust is shown in Fig. 3.
Crop environment is composed of information obtained from the weather data provider METEOBLUEFootnote 2 and crop properties entered by farmers. This information is stored and constitutes the main resource of the expert system for the detection of coffee rust favorable conditions in crops. This system identifies crop conditions for a given infection rate of the disease, as detailed in [31, 32]. Once the DSS is consulted, the expert system checks whether the crop has favorable conditions for the disease. On the other hand, the Data Analysis component also makes use of weather and crop data stored, processed through rules and expert knowledge, in order to recognize the properties of the elements that make up the disease control. The Interpretation module identifies the state of the crop against the disease and combines this information with the suggested process for its control, resulting in the generation of alternatives that the farmer can take.
3.2 Deployment
AgroCloudFootnote 3 represents a cloud-based platform to support the development of information services for the Colombian agricultural sector and an early warning system to reduce vulnerability to variability and climate change phenomena. The platform is focused on the municipalities located in the upper basin of the Cauca River. The main components of the platform are: weather monitoring, weather forecasting, support for decision-making, Expert System (ES) and reports.
Weather monitoring is carried out from a subscription to a climate data provider, obtaining values of weather variables such as: air temperature, relative humidity, wind speed and direction, rainfall and solar radiation. The information is queried through the data provider API and stored in the AgroCloud databases.
The Decision Support System (DSS) makes use of computational tools to analyze the variables that intervene in crop diseases and to generate a decision that implements the alternative with more probability to be successful. As a specific case, the DSS has been developed for the management of Coffee Rust control and the costs of its application, as is described by Lasso and Corrales in [33].
The ES integrates the information that has been collected by the previous components (weather monitoring and forecasting, support for decision-making) for alerting on the presence of favorable conditions for the occurrence of rust in coffee crops. Once the parameters corresponding to the validity of the data are verified, an alert is communicated to the involved actors. This system corresponds to an implementation of the expert system for coffee rust proposed by Lasso and Corrales in [31, 32], which makes use of graph patterns for the disease presented by the same author in [14].
Finally, the agroclimatic reports correspond to structured documents on the climatic conditions presented in a municipality, identifying significant events in different time periods. Additionally, reports may also characterize conditions for historically identified diseases.
The layered view of the architecture is shown in Fig. 4 and its components are described below.
-
Weather data provider: AgroCloud obtains the weather information in the municipalities from the weather data provider METEOBLUE, which delivers local weather data for any point in the world. It offers a web-based access interface consulted periodically, providing the values of different climate variables such as: temperature, rainfall, humidity, wind, among others.
-
Persistence layer: Databases for the storage of several elements in crops environment, such as: Weather data, obtained from data provider described previously; Crops, that contains crop properties, agro-production management; and Users database, which contains the information of AgroCloud users according to the organizational structure of the production system. Additionally, in this layer the knowledge base for disease detection (early warning services) and control (decision-making support), obtained from experts knowledge is stored.
-
Service layer: This layer is comprised of high granularity services (HGS), an enterprise service bus (ESB), and value-added services (VAS). The HGS are divided according to the nature of the functions that they offer. In this way, the agroclimatic (relationship between crop adaptation and climate) services provide the visualization and recovery of the weather monitoring data, forecast services and the report generation. The ESB allows the reuse of functions offered by the HGS, enabling the integration between different areas covered by AgroCloud (weather monitoring, disease detection and control). As a result, several VAS are obtained modeled as business process.
-
View layer: Represents the interfaces for user interaction according the different services mentioned above. The Web platform and the Mobile application represent the main interaction, built based on elements of easy use and understanding for the different user roles. Telco refers to traditional telecommunication services, such as automatic voice calls and SMS (Short Message Service), as a communication channel for sensitive events for crops such as identification of favorable disease conditions. E-mail component is an element mainly used by the reporting system, allowing periodic and cost-free communication of significant events found in the influence area covered by the platform.
4 Results
End users are the main actors who interact with a product daily and constantly. Therefore, their satisfaction is one of the most important measures of the final product success; in particular those systems that support decision making and provide important information from the expert knowledge in a productive sector such as agribusiness. This section presents the User Acceptance Testing (UAT) methodology [34] and the main elements to take into account for validation of AgroCloud which comprises weather services, detection of favorable conditions for diseases, and the DSSEx component.
UAT is the last phase of the validation process of a software solution. This methodology intends to analyze, from the use of the application by end users, if there are failures in responses and input forms, usability, correspondence with the problem that tries to solve, and the impact on it. From the UAT theoretical basis, the application of this methodology specifically in the AgroCloud platform is presented below.
4.1 Type of Test
In the execution of UAT was used the concept of “black box”, which is commonly categorized as a functional test, but can also be used for UAT. Users only know and interact with the system inputs and outputs, without being able to see the code and internal flow of operation. In addition, the end user knows the business requirements. This test was developed from meetings where each user used the system through a computer. In cases where the user group exceeded 10 people, the use of the system was projected so that everyone could perceive the process and answers obtained.
4.2 UAT Users
In the coffee production environment, there are 3 types of users directly related to the treatment and control of the crop. UAT was applied to 53 users (Fig. 5) and their characteristics are described below.
-
Producers. Refers to the small, medium or large farmer, depending on the level of production. In addition, there are associations that seek to join efforts to carry out an orderly and articulated production. 5 medium-sized producers from Cajibío (Cauca), an association of organic coffee producers (Popayán) (12 producers), and an association of coffee growers from Los Andes - Corinto (ASPROCCAN) (20 producers).
-
Agricultural Extension Officers (AEO). Staff with technical knowledge in coffee production, delegates by the Coffee Growers Federation to advise producers on different problems around the process. A technical assistance group of the National Federation of Coffee Growers (Colombia) was interviewed (15 users).
-
Researchers. They are usually agronomists who study the phenomena that affect coffee production and how to solve them. An agronomist was interviewed for UAT.
4.3 Business Requirements
Provide relevant climatic information such as current conditions, historical data, weather forecast, among others. Additionally, support the selection of type of fungicide and spray system to be used to counteract the impact of coffee rust disease. This choice was based on costs comparison of possible available combinations in the market by budget per application and year. On the other hand, the expert system requirement is to detect favorable conditions for diseases (case study of coffee rust) in the upper basin of Cauca River municipalities.
4.4 Test Cases
Before defining the test cases that allowed to validate the AgroCloud platform, it is necessary to mention the lack of climatic data in the study area for the periods when the test was executed. Taking into account this, it was necessary to define an adaptation scheme of the systems and their sources of information to carry out the simulation of the different possible scenarios around rust epidemics. In this way, data from a weather station and disease monitoring in a pilot coffee farm were used to simulate scenarios that favored rust, based on knowledge stored in the expert system. Based on the above considerations, test cases are shown below.
Favorable Conditions
-
Listing of favorable conditions for diseases.
-
View details of a favorable condition.
-
Access rust control management from the details of a favorable condition.
Control Management
-
Get recommendation of the fungicide application moment according to the flowering period.
-
Access to cost management from the recommendation of the type of fungicide.
-
Get recommendation of the fungicide application moment according to the fixed calendar system.
-
Access to cost management from the recommendation of implementation dates by fixed calendar system.
-
Obtain recommendation of the fungicide application moment according to the level of rust infection.
-
Get current recommendations on the fungicide application technology for rust control.
Cost Management
-
Obtain costs for a known control system.
-
Get cost comparison for different control system options (fungicide and spraying equipment).
-
View details of a control system configuration costs.
Weather Services
-
Get current conditions of a municipality.
-
Get the historical data of a municipality.
-
Get the weather forecast of a municipality.
Additionally, four questions about each test case were applied. The number of users by user type who answered affirmatively to each of these questions are shown in Fig. 6.
-
Q1: Was the task completed satisfactorily?
-
Q2: Did the user require assistance to complete the task satisfactorily?
-
Q3: Were the information request forms satisfactorily understood?
-
Q4: Users consider the tool useful?
From results shown in the previous figure, it is possible to establish that the AgroCloud platform presents relevant information for users at a high level. However, cost management and weather services were not completely understandable by producers and AEO user groups. In this sense, improving the usability of these services becomes a key aspect for all user groups to obtain the greatest benefit in their decision-making processes. Similarly, some users needed technical assistance to complete the tasks of all AgroCloud services, in particular the producer group to complete the tasks of all AgroCloud components. These aspects evidenced the need to improve the platform help menus according to the obtained feedback. Therefore, it is important to take into account the users recommendations and comments in order to analyze and determine which changes allow to increase the comprehensibility level of the platform.
5 Conclusions and Future Works
Systems aimed at solving problems in agricultural production environments are challenged not only to generate the best recommendation, but also to generate an environment of easy understanding and usability for all possible roles and actors present. The interaction between the development team and producers allows us to know the concerns of the main users and generate ideas to further develop new functionalities in order to improve the system. Recommendations and comments obtained in the UAT allowed to define different guidelines to improve the platform (utility and usability) for the end users in an agricultural environment.
Among the main recommendations obtained from UAT that will be taken into ac-count for the improvement of the platform, are: (i) take into account other diseases such as South America leaf spot and brown leaf spot, in addition to pests, (ii) recommendations to improve the fertilization of crops, (iii) recommendation of plan nutrition from digital analysis of its leaves photos, (iv) take into account other crops, (v) address nutrition and fertilization in crops, (vi) producers want to take advantage of the soil analysis they have on their farms. The above considerations must be accompanied by the incorporation of an autochthonous written and celestial language that can be understood and assimilated by the group of producers (words, phrases, symbols, images, among others that are handled within a rural community).
As a future work, real and close to real time data are required in order to improve the decisions-making process. Similarly, significant weather events should be exclusively related to the selected station or municipality. On the other hand, add a comparison section of hourly, daily, monthly, and annual data; and to show the maximum and minimum values of the meteorological variables. Finally, regarding the detection of favorable conditions for diseases, users recommended that detections should be sent by Short Message Service (SMS) or, if possible, by a message from a social network like WhatsApp, Facebook, or Twitter.
Notes
- 1.
- 2.
- 3.
Available in https://agrocloudcolombia.com.
References
Colombia siembra. Cientific DE-DEI-11, Ministerio de Agricultura y Desarrollo Rural (2016)
Piza, C., Diaz, L.P., Pulido, N., Rincon, R.J.D.: Agricultura familiar: una alternativa para la seguridad alimentaria. Conexion Agropecuaria JDC, 6(1), September 2016
Fernandez, M.: Efectos del cambio climtico en la produccion y rendimiento de cultivos por sectores. Cientific 2130628, IDEAM (2013)
Avelino, J., Cristancho, M., Georgiou, S., Imbach, P., Aguilar, L., Bornemann, G., Läderach, P., Anzueto, F., Hruska, A.J., Morales, C.: The coffee rust crises in colombia and central america (2008–2013): impacts, plausible causes and proposed solutions. Food Secur. 7(2), 303–321 (2015)
Corrales, D.C., Pena, A., Leon, C., Figueroa, A., Corrales, J.C.: Early warning system for coffee rust disease based on error correcting output codes: a proposal. Revista Ingenierias Universidad de Medellin 13, 57–64 (2014)
Rivillas, C., Serna, C., Cristancho, M., Gaitan, A.: La Roya del Cafeto en Colombia. Impacto, manejo y costos de control. Cientific bot036, Cenicafe (2011)
Corrales, D.C., Gutierrez, G., Rodriguez, J.P., Ledezma, A., Corrales, J.C.: Lack of Data: Is It Enough Estimating the Coffee Rust with Meteorological Time Series? pp. 3–16. Springer International Publishing, Cham (2017)
Keen, P.G.W., Morton, M.S.S.: Decision Support Systems: An Organizational Perspective. Addison-Wesley series on decision support, Addison-Wesley Pub. Co. (1978)
Agrios, G.N.: Plant Pathology. Academic press, New York (1997)
Plumb, R.: Precision agriculture in the 21st century: geospatial and information technologies in crop management, committee on assessing crop yield: site-specific farming, information systems and research opportunities, board on agriculture. Pest Management Science 56(8), 723–723 (2000). National research council, National academy press, Washington DC, USA 1997, xii+ 149 pp, price£ 32.95. ISBN 0-309-05893-7
Corrales, D.C., Figueroa, A., Ledezma, A., Corrales, J.C.: An Empirical Multi-classifier for Coffee Rust Detection in Colombian Crops, pp. 60–74. Springer International Publishing, Cham (2015)
Corrales, D.C., Ledezma, A., Pea, Q.A.J., Hoyos, J., Figueroa, A., Corrales, J.C.: A new dataset for coffee rust detection in Colombian crops base on classifiers. Sistemas y Telemtica 12(29), 9–23 (2014)
Corrales, D.C., Casas, A.F., Ledezma, A., Corrales, J.C.: Two-level classifier ensembles for coffee rust estimation in colombian crops. Int. J. Agric. Environ. Inf. Syst. (IJAEIS) 7(3), 41–59 (2016)
Lasso, E., Thamada, T.T., Meira, C.A.A., Corrales, J.C.: Graph Patterns as Representation of Rules Extracted from Decision Trees for Coffee Rust Detection, pp. 405–414. Springer International Publishing, Cham (2015)
Plazas, J.E., Rojas, J.S., Corrales, D.C., Corrales, J.C.: Validation of Coffee Rust Warnings Based on Complex Event Processing, pp. 684–699. Springer International Publishing, Cham (2016)
Meira, C.A.A., Rodrigues, L.H.A., Almeida, S., de Moraes., S.A.: Warning models for coffee rust control in growing areas with large fruit load. Pesquisa Agropecuaria Brasileira 44(3), 233–242 (2009)
Luaces, O., Rodrigues, L.H.A., Meira, C.A.A., Quevedo, J.R., Bahamonde, A.: Viability of an alarm predictor for coffee rust disease using interval regression. In: Garca-Pedrajas, N., Herrera, F., Fyfe, C., Bentez, J.M., Ali, M. (eds.) Trends in Applied Intelligent Systems. Lecture Notes in Computer Science, vol. 6097, pp. 337–346. Springer, Heidelberg (2010)
Cintra, M.E., Meira, C.A.A., Monard, M.C., Camargo, H.A., Rodrigues, L.H.A.: The use of fuzzy decision trees for coffee rust warning in Brazilian crops. In: 2011 11th International Conference on Intelligent Systems Design and Applications (ISDA), pp. 1347–1352, November 2011
Luaces, O., Rodrigues, L.H.A., Meira, C.A.A., Bahamonde, A.: Using nondeterministic learners to alert on coffee rust disease. Expert Syst. Appl. 38(11), 14276–14283 (2011)
Perez-Ariza, C., Nicholson, A., Flores, M.: Prediction of coffee rust disease using Bayesian networks. pp. 259–266. DECSAI University of Granada (2012)
Small, I.M., Joseph, L., Fry, W.E.: Development and implementation of the blightpro decision support system for potato and tomato late blight management. Comput. Electron. Agric. 115, 57–65 (2015)
Rossi, V., Salinari, F., Poni, S., Caffi, T., Bettati, T.: Addressing the implementation problem in agricultural decision support systems: the example of vite. net®. Comput. Electron. Agric. 100, 88–99 (2014)
Navarro-Hellín, H., Martínez-del Rincon, J., Domingo-Miguel, R., Soto-Valles, F., Torres-Sánchez, R.: A decision support system for managing irrigation in agriculture. Comput. Electron. Agric. 124, 121–131 (2016)
Dandawate, Y., Kokare, R.: An automated approach for classification of plant diseases towards development of futuristic decision support system in indian perspective. In: 2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI), pp. 794–799. IEEE (2015)
Cañadas, J., Sánchez-Molina, J.A., Rodríguez, F., del Águila, I.M.: Improving automatic climate control with decision support techniques to minimize disease effects in greenhouse tomatoes. Inf. Process. Agric. 4(1), 50–63 (2017)
Waghmare, H., Kokare, R., Dandawate, Y.: Detection and classification of diseases of grape plant using opposite colour local binary pattern feature and machine learning for automated decision support system. In: 2016 3rd International Conference on Signal Processing and Integrated Networks (SPIN), pp. 513–518. IEEE (2016)
Antonopoulou, E., Karetsos, S.T., Maliappis, M., Sideridis, A.B.: Web and mobile technologies in a prototype DSS for major field crops. Comput. Electron. Agric. 70(2), 292–301 (2010). Special issue on Information and Communication Technologies in Bio and Earth Sciences
Stray, B.J., Van Vuuren, J.H., Bezuidenhout, C.N.: An optimisation-based seasonal sugarcane harvest scheduling decision support system for commercial growers in south africa. Comput. Electron. Agric. 83, 21–31 (2012)
Jarroudi, M.E.L., Kouadio, L., Beyer, M., Junk, J., Hoffmann, L., Tychon, B., Maraite, H., Bock, C.H., Delfosse, P.: Economics of a decision-support system for managing the main fungal diseases of winter wheat in the grand-duchy of luxembourg. Field Crops Res. 172, 32–41 (2015)
Molitor, D., Augenstein, B., Mugnai, L., Rinaldi, P.A., Sofia, J., Hed, B., Dubuis, P.-H., Jermini, M., Kührer, E., Bleyer, G., et al.: Composition and evaluation of a novel web-based decision support system for grape black rot control. Eur. J. Plant Pathol. 144(4), 785–798 (2016)
Lasso, E., Thamada, T.T., Meira, C.A.A., Corrales, J.C.: Expert system for coffee rust detection based on supervised learning and graph pattern matching. Int. J. Metadata Semant. Ontol. (2017, to appear)
Lasso, E., Corrales, J.C.: Expert system for crop disease based on graph pattern matching: a proposal. Revista Ingenieras Universidad de Medellin 15(29), 81–98 (2016)
Lasso, E., Valencia, Ó., Corrales, J.C.: Decision Support System for Coffee Rust Control Based on Expert Knowledge and Value-Added Services, pp. 70–83. Springer International Publishing, Cham (2017)
Cimperman, R.: UAT Defined: A Guide to Practical User Acceptance Testing, 1st edn. Addison-Wesley Professional, Boston (2006)
Acknowledgments
The authors are grateful to the University of Cauca and its Telematics Engineering Group (GIT), the Colombian Administrative Department of Science, Technology and Innovation (Colciencias) and AgroCloud project of The Interinstitutional Network of Climate Change and Food Security of Colombia (RICCLISA) for supporting this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Lasso, E., Valencia, O., Corrales, D.C., López, I.D., Figueroa, A., Corrales, J.C. (2018). A Cloud-Based Platform for Decision Making Support in Colombian Agriculture: A Study Case in Coffee Rust. In: Angelov, P., Iglesias, J., Corrales, J. (eds) Advances in Information and Communication Technologies for Adapting Agriculture to Climate Change. AACC'17 2017. Advances in Intelligent Systems and Computing, vol 687. Springer, Cham. https://doi.org/10.1007/978-3-319-70187-5_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-70187-5_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70186-8
Online ISBN: 978-3-319-70187-5
eBook Packages: EngineeringEngineering (R0)