Abstract
Wetland destruction is currently one of the greatest environmental problems in the world. Despite the functions of wetlands, these valuable ecosystems have steadily decreased because of human activities and climate change. To protect these valuable ecosystems, wetland restoration and rehabilitation are important operations that have been conducted worldwide. Since a wetland is a complex ecosystem with a variety of phenomena, increasing the number of variables considered during a restoration project will further boost the success rate of a restoration project. However, the inclusion of more variables will increase the complexity of the analysis. Thus, a method that can analyze complex models using many input variables is valuable. In most scientific studies, artificial intelligence algorithms have been widely applied to complex projects. However, the main question is whether these algorithms can learn the ecological patterns of a restoration project. For this reason, a multilayer perceptron (MLP) neural network was applied in this paper to investigate the ability to use these algorithms for wetland restoration. An artificial neural network (ANN) with one hidden layer and 15 neurons was used to determine the best areas for wetland restoration. The neural network was trained using the Levenberg-Marquardt algorithm; then, the trained ANN was used to determine the best areas for wetland restoration. The root mean square error (RMSE) of the model that was trained to prioritize wetland restoration was 0.04 ha. Because of water limitations in the study area, it is not possible to restore entire wetlands. Therefore, areas for restoration are prioritized based on ecological objectives. The results of the ANN demonstrate its ability to learn the ecological patterns and illustrates the performance of using this method for wetland restoration. Neural networks can calculate the final weights mathematically, and these algorithms are able to analyze complex models using many input variables; thus, ANNs are practical for wetland restoration.
Similar content being viewed by others
References
Abbasi B, Mahlooji M (2012) Improving response surface methodology by usingartificial neural network and simulated annealing. Expert System with Applications 39:3461–3468
Ackerman S (1989) Using the radiative temperature difference at 3.7 and 11 μm to tract dust outbreaks. Remote Sensing of Evironment 27:129–133
Ackerman S (1997) Remote sensing aerosols using satellite infrared bservations. Journal of Geophysical Research 8:100–115
Babbar M, Barr R, Tedesco L, Anderson M (2013) Spatial identification and optimization of upland wetlands in agricultural watersheds. Ecological Engineering 52:130–142
Baddock M, Bullard J, Bryant R (2009) Dust source identification usingMODIS: a comparison of techniques applied to the Lake Eyre Basin, Australia. Remote Sensing of Environment 113:1511–1528
Baeza C, Lantada N, Amorimc S (2016) Statistical and spatial analysis of landslide susceptibility maps with different classification systems. Environmental Earth Sciences 75:20–54
Baghdadi N, Bernier M, Gauthier R, Neeson I (2001) Evaluation of C-band SAR data for wetlands mapping. International Journal of Remote Sensing 22:71–88
Betbeder J, Rapinel S, Corpetti T (2013) Multi-temporal classification of TerraSAR-X data for wetland vegetation mapping. SPIE Remote Sensing 29(8887):88871
Bisht D, Jain S, Raju M (2013) Prediction of water table elevation fluctuation through Fuzzy Logic & Artificial Neural Networks. International Journal of Advanced Science and Technology 51:107–120
Brander LM, Florax JGM, Vermaat JE (2006) The empirics of wetland valuation: a comprehensive summary and meta-analysis of the literature. Environmental and Resource Economics 33:223–250
Chen KT (2014) Close-loop or open hierarchicalstructures in green supply chain management under uncertainty. Expert Systems with Applications 41:3250–3260
Chen J, Lin S (2003) An interactive neural network-based approach for solving multiple criteria decision-making problems. Decision Support Systems 36:137–146
Cipollini KA, Maruyama AL, Zimmerman CL (2005) Planning for restoration a decision analysis approach to prioritization. Restoration Ecology 13(3):460–470
Darwiche N, Sorando R, Eismann S, Comin F (2017) Comparing two multi-criteria methods for prioritizing wetland restoration and creation sites based on ecological, biophysical and socio-economic factors. Water Resoure Management 31:1227–1241
Dipon D, Tom S, Soonwook H (2016) Neural architecture of hunger-dependent multisensory decision making in C. elegans. International Journal of Computer and Information Technology 92(5):1049–1062
El-Bakyr MY (2003) Feed forward neural networks modeling for K-P interactions. Chaos, Solutons and Fractals 18:995–1000
Golmohammadi D (2011) Neural network application for fuzzy multi-criteria deci-Sion making problems. International Journal of Production Economics 131:490–504
Golmohammadi D, Mellat-Parast M (2012) Developing a grey-based decision-making model for supplier selection. International Journal of Production Economics 137:191–200
Golmohammadi D, Creese R, Valian H, Kolassa J (2009) Supplier selection basedon a neural network model using genetic algorithm. IEEE Transactions on Neural Networks 20:1504–1519
Guo Z, Wu J, Lu H, Wang J (2011) A case study on a hybrid wind speed forecasting method using BP neural network. Knowledge-Based Systems 24:1048–1056
Guo M, Li J, Sheng C, Xu J, Wu L (2017) A review of wetland remote sensing. Sensor 17:100–136
Hagan MT, Menhaj MB (1994) Training feed forward networks with the Marquardt algorithm. IEEE Transaction Neural Networks and Spatial Economics 6:861–867
Holzmueller EJ, Gaskins MD, Mangun JC (2011) A GIS approach to prioritizing habitat for restoration using neotropical migrant songbird criteria. Environmental Management 48(1):150–157
Kamer E, Carpendo S (2009) A statewide approach for identifying potential areas for wetland restoration and mitigation banking in Georgia. In Georgia water resources conference, 4 April 2009. University of Georgia. PP.32–41
Karsoliya S (2012) Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture. International Journal of Engineering Trends and Technology 3:714–725
Kauffman-Axelrod JL, Steinberg SJ (2010) Development and application of an automated GIS based evaluation to prioritize wetland restoration opportunities. Wetlands 30(3):437–450
Klemas V (2013) Using remote sensing to select and monitor wetland restoration sites: an overview. Journal of Coastal Research 29:958–970
Kumar K, Kumari K, Bhaskar P (2013) Artificial neural network model for prediction of land surface temperature from land use/cover images. International Journal of Advanced Trends in Computer Science and Engineering 2:87–92
Laporte A, Weersink A, Yang W (2010) Ecological goals and wetland preservation choice. Canadian Journal of Agricultural Economics 58:131–150
Li X, Li C, Zhang L (2010) Modeling the scenarios of wetland restoration in Hengshui Lake National Nature Reserve. Procedia Environmental Sciences 2:1279–1289
Maduako I, Yun Z, Patrick B (2016) Simulation and prediction of land surface temperature (LST) dynamics within Ikom City in Nigeria using artificial neural network (ANN). Journal of Remote Sensing and GIS 31–38
Malczewski J, Rinner C (2015) Multicriteria decision analysis in geographic information science. Springer, New York
Maleki S, Soffianian A, Koupaei SS, Saatchi S, Pourmanafi S, Sheikholeslam F (2016) Habitat mapping as a tool for water birds conservation planning in an arid zone wetland: the case study Hamoun wetland. Ecological Engineering 95:594–603
Maleki S, Soffianian AR, Soltani-Koupaei S, Pourmanafi S, Saatchi S (2018) Wetland restoration prioritizing, a tool to reduce negative effects of drought; An application of multicriteria-spatial decision support system (MC-SDSS). Ecological Engineering 112:132–139
Marquardt D (1963a) An algorithm for least squares estimation of non-linear parameters. Journal of the Society for Industrial and Applied Mathematics Series A Control 29:431–441
Marquardt D (1963b) An algorithm for least squares estimation of non-linear parameters. Journal of the Society for Industrial and Applied Mathematics 29:431–441
Miao H, Guo Y, Zhong G, Liu B, Wang G (2018) A novel model of estimating sea state bias based on multi-layer neural network and multi-source altimeter data. European Journal of Remote Sensing 51(1):616–626
Mitsch W, Gosselink J (2007) Wetlands. Wiley, New York
Nicholls RJ (2004) Coastal flooding and wetland loss in the 21st century: changes under the SRES climate and socio-economic scenarios. Global Environmental Change 14:69–86
O'Neill M, Hawkins C, Russell G (1997) Identifying sites for riparian wetland restoration. Restoration Ecology 5:85–102
Ouyang NL, Lu S, Wu B, Zhu J, Wang H (2011) Wetland restoration suitability evaluation at the watershed scale- a case study in upstream of the Yongdinghe River. Procedia Environmental Sciences 10:1926–1932
Ozgur K (2004) Multi-layer perceptrons with Levenberg-Marquardt training algorithm for suspended sediment concentration prediction and estimation. Hydrological Sciences 49:1025–1040
Özkana G, Inal M (2014) Comparison of neural network application for fuzzy and ANFISapproaches for multi-criteria decision making problems. Applied Soft Computing 24:232–238
Palmeri L, Trepel M (2002) A GIS-based score system for siting and sizing of created or restored wetlands: two case studies. Water Resources Management 16:307–328
Partow H (2003) Oasis parched by drought. In Atlas of global change. In: Program, U.N.E. (Ed.), Oxford University Press
Rahdari V, Maleki S, Abtin E (2014) Investigation the potential of satellite data for wetland zoning. Journal of Wetland Ecobiology 5(4):67–78
Ramsar Convention Secretariat (2006) World Wetlands Day 2006 in the Islamic Republic of Iran
Ramsar Convention Secretariat (2016) The List of Wetlands of International Importance
Ren J, Yan W, Wang Y (2007) The satellite altimeter wind speed retrieval algorithm based on neural network. Journal of Marine Technology 26:47–50
Sedighi M, Keyvanloo K, Towfighi J (2011) Modeling of thermal cracking of heavyliquid hydrocarbon: application of kinetic modeling, artificial neural network,and neuro-fuzzy models. Industrial Engineering 50:1536–1547
Shahraiyni HT, Karimi K, Nokhandan MH, Moghadas NH (2015) Monitoring of dust storm and estimation of aerosol concentration in the Middle East using remotely sensed images. Arabian Journal of Geosciences 8:2095–2110
Shamohammadi Z, Maleki S (2011) Iranian student book agancy. Tehran, Iran. 52-83.
Silva S, Alçada-Almeida L, Dias LC (2014) Biogas plants site selection integrating multicriteria decision aid methods and GIS techniques: a case study in a Portuguese region. Biomass and Bioenergy 71:58–68
Smith S, Medeiros K (2012) Manipulation of water levels to facilitate vegetation change in a coastal lagoon undergoing partial tidal restoration (Cape Cod, Massachusetts). Journal of Coastal Research 25:23–36
Sun X, Xiong S, Zhu J, Zhu X, Li Y (2015) A new indices system for evaluating ecological-economic-social performances of wetland restorations and its application to Taihu Lake Basin, China. Ecological Modelling 295:216–226
Taravat A, Rajaei M, Emadodin I, Hasheminejad H, Mousavian R, Biniyaz E (2016) A spaceborne multisensory, multitemporal approach to monitor water level and storage variations of lakes. Water 8(11):478
Tegen I (2003) Modeling the mineral dust aerosol cycle in the climate system. Quaternary Science Reviews 22:1821–1834
UNEP (2014) Hamoun wetlands: current situation and the way forward. United Nations Environment Programme; PO Box 30552, Nairobi, Kenya. Information Sheet dated March 20, 2014; 5 pages
White D, Fennessy MS (2005) Modeling the suitability of wetland restoration potential at the watershed scale. Ecological Engineering 24:359–377
Widis DC, BenDor TK, Deegan M (2015) Prioritizing wetland restoration sites: a review and application to a large- scale coastal restoration Program. Ecological Restoration 33:358–377
Delft Hydraulics and WRC (2003) Final and main report sistan flood warning and emergency plan for Sistan-Baluchestan Regional Water Authority.
Meijer, K., van Beek, E., and Roest, K. (2006). Integrated water resources managment for the Sistan Closed Inland Delta, Iran, ANNEX C: Sistan water resourced system: supply and demand. Accessed Apr 2006
Wulder MA, Hall RJ, Coops NC, Franklin SE (2004) High spatial resolution remotely sensed data for ecosystem characterization. Bioscience 54:511–521
Zhang F, Song Y (2014) Optimization of wetland restoration siting and zoning in flood retention areas of river basins in China: a case study in Mengwa, Huaihe River basin. Journal of Hydrology 519:80–93
Zhang GP, Patuwo BE, Hu MY (2001) A simulation study of artificial neural networks for nonlinear time series forecasting. Computers and Operations Research 28:23–35
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix: Operating principle of Multi Layers Perceptron (MLP) neural network
Appendix: Operating principle of Multi Layers Perceptron (MLP) neural network
Appendix Fig. 10 represents a MLP neural network with a single hidden layer.
A one-hidden-layer MLP can be described as a function f : RD → RL, where D is the size of input vector x and L is the size of the output vector f(x), such that, in matrix notation:
with bias vectors b(1), b(2); weight matrices W(1), W(2) and activation functions G and s (Taravat et al. 2016).
The vector h(x) = Φ(x) = s(b(1) + W(1)x) constitutes the hidden layer.
\( {W}^{(1)}\in {R}^{D\times {D}_h} \) is the weight matrix connecting the input vector to the hidden layer.
Typical choices for s include tanh, with tanh(a) = (ea − e−a)/(ea + e−a), or the logistic sigmoid function, with sigmoid(a) = 1/(1 + e−a).
The output vector is then obtained as: o(x) = G(b(2) + W(2)h(x)). As before, class-membership probabilities can be obtained by choosing G as the softmax function (in the case of multi-class classification) (Taravat et al. 2016).
The set of parameters to learn the algorithm is the set θ = {W(2), b(2), W(1), b(1)}. Obtaining the gradients ∂ℓ/∂θ can be achieved through the backpropagation algorithm (Taravat et al. 2016).
Tan-Sigmoid transfer function from the input layer to the hidden layer is used (Guo et al. 2011; Miao et al. 2018):
For the transfer function from the hidden layer to the output layer, the pure-linearity expression is applied as follows (Ren et al. 2007):
where k is a non-zero real number and b is the bias term.
Appendix Fig. 11. illustrates the major transfer functions.
Rights and permissions
About this article
Cite this article
Maleki, S., Soffianian, A.R., Koupaei, S.S. et al. Wetland Restoration Prioritization Using Artificial Neural Networks. Wetlands 40, 179–192 (2020). https://doi.org/10.1007/s13157-019-01165-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13157-019-01165-8