Application of Artificial Neural Networks to Optimize Nitrogen Supply to Meet Plant Needs for Soil Conservation: Case Study, M’Bahiakro Irrigated Perimeter (Central-East, Ivory Coast)
The low nitrogen content of soils in the rice-growing area of M’Bahiakro requires optimized fertilization to improve yields while minimizing environmental impacts. This study proposes an intelligent model based on backpropagation neural networks (BPNN) to predict the nitrogen requirements of rice using seven physico-chemical soil parameters (K, P, Norg, OM, θpf, CEC, and Kc). The model was trained using the Levenberg-Marquardt algorithm, with a sigmoid transfer function for the hidden layer and a linear function for the output layer. Model performance was evaluated using the coefficient of determination (R2 = 0.98) and the mean squared error (MSE = 0.001), indicating high predictive accuracy. Results show that rice yield no longer improves significantly beyond 118 kg N？ha？1, with R2 and MSE values stabilizing around 98% and 0.007, respectively. This threshold therefore represents an optimal nitrogen dose, enabling a balance between agricultural productivity and the preservation of natural resources, particularly by reducing soil degradation and groundwater contamination. However, to strengthen the model’s robustness, further investigations are essential in the irrigated area of M’Bahiakro, especially during the dry season. Expanding the study to include other rice varieties, soil types, and cultivation practices would not only broaden the model’s applicability but also reinforce its role as a decision-support tool in sustainable nitrogen fertilization strategies.
References
[1]
Yuan, S., Saito, K., van Oort, P.A.J., van Ittersum, M.K., Peng, S. and Grassini, P. (2024) Intensifying Rice Production to Reduce Imports and Land Conversion in Africa. NatureCommunications, 15, Article No. 835. https://doi.org/10.1038/s41467-024-44950-8
[2]
FAO (2016) Producing More with Less in Practice. Maize-Rice-Wheat: A Guide to Sustainable Cereal Production. (In French)
[3]
Xu, G., Fan, X. and Miller, A.J. (2012) Plant Nitrogen Assimilation and Use Efficiency. AnnualReviewofPlantBiology, 63, 153-182. https://doi.org/10.1146/annurev-arplant-042811-105532
[4]
Li, H., Hu, B. and Chu, C. (2017) Nitrogen Use Efficiency in Crops: Lessons from Arabidopsis and Rice. JournalofExperimentalBotany, 68, 2477-2488. https://doi.org/10.1093/jxb/erx101
[5]
Han, M., Okamoto, M., Beatty, P.H., Rothstein, S.J. and Good, A.G. (2015) The Genetics of Nitrogen Use Efficiency in Crop Plants. AnnualReviewofGenetics, 49, 269-289. https://doi.org/10.1146/annurev-genet-112414-055037
[6]
Becker, M. and Johnson, D.E. (2001) Improved Water Control and Crop Management Effects on Lowland Rice Productivity in West Africa. NutrientCyclinginAgroecosystems, 59, 119-127. https://doi.org/10.1023/a:1017585328904
[7]
Kotchi, J.K., Ouattara-Coulibaly, Y.R. and N’guessan, G.K. (2018) Impact socio-économique de l’aménagement hydro-rizicole de Guiguidou dans la sous-préfecture de Divo (Côte d’Ivoire). EchoGéo, 43, 1-18. https://doi.org/10.4000/echogeo.15275
[8]
SNDR (2012) Revised National Strategy for the Development of the Rice Sector in Côte d’Ivoire (SNDR) 2012-2020. Ministry of Agriculture, Ivory Coast. https://riceforafrica.net/wp-content/uploads/2021/09/Cote_dIvoire_en.pdf
[9]
Silué, P.D. and Dago, D.N. (2014) Dynamics of the Natiokobadara Dam Water Level and Rice Production in Northern Ivory Coast. AfricanJournalofScientificandTechnologicalCommunication, 27, 3571-3580. (In French)
[10]
Baï, R., Kouame, I.K., Kouassı, L.K., Konan, S.K. and N’Cho, H.A. (2019) Assessment of the Physicochemical Quality of Irrigation Water and Soil for Sustainable Irrigated Rice Cultivation: Case of Irrigated Perimeter of M’bahiakro (Central-East of Côte d’Ivoire). JournalofEnvironmentalProtection, 10, 1536-1552. https://doi.org/10.4236/jep.2019.1011091
[11]
Kouassi, L.K., Kouamé, I.K., Konan, S.K., Dibi, B., Moussa, S., Koné, D., etal. (2013) Prospects for Minimizing the Potential Environmental Impacts of the Hydro-Agricultural Dam of M’bahiakro (côte d’Ivoire). JournalofWaterResourceandProtection, 5, 847-853. https://doi.org/10.4236/jwarp.2013.59085
[12]
Carriger, J.F., Rand, G.M., Gardinali, P.R., Perry, W.B., Tompkins, M.S. and Fernandez, A.M. (2006) Pesticides of Potential Ecological Concern in Sediment from South Florida Canals: An Ecological Risk Prioritization for Aquatic Arthropods. SoilandSedimentContamination: AnInternationalJournal, 15, 21-45. https://doi.org/10.1080/15320380500363095
[13]
Kibblewhite, M.G., Ritz, K. and Swift, M.J. (2007) Soil Health in Agricultural Systems. PhilosophicalTransactionsoftheRoyalSocietyB: BiologicalSciences, 363, 685-701. https://doi.org/10.1098/rstb.2007.2178
[14]
Bitew, Y. and Alemayehu, M. (2017) Impact of Crop Production Inputs on Soil Health: A Review. AsianJournalofPlantSciences, 16, 109-131. https://doi.org/10.3923/ajps.2017.109.131
[15]
Jahan, M. and Amiri, M.B. (2018) Optimizing Application Rate of Nitrogen, Phosphorus and Cattle Manure in Wheat Production: An Approach to Determine Optimum Scenario Using Response-Surface Methodology. Journalofsoilscienceandplantnutrition, 18, 13-26. https://doi.org/10.4067/s0718-95162018005000102
[16]
Agbo, C., Chukwudi, P.U. and Ogbu, A.N. (2012) Effects of Rates and Frequency of Application of Organic Manure on Growth, Yield and Biochemical Composition of Solanummelongena L. (cv. ‘Ngwa local’) Fruits. JournalofAnimal&PlantSciences, 2, 1952-1960.
[17]
Parent, S., Lafond, J., Paré, M.C., Parent, L.E. and Ziadi, N. (2020) Conditioning Machine Learning Models to Adjust Lowbush Blueberry Crop Management to the Local Agroecosystem. Plants, 9, Article 1401. https://doi.org/10.3390/plants9101401
[18]
Coulibali, Z., Cambouris, A.N. and Parent, S. (2020) Site-Specific Machine Learning Predictive Fertilization Models for Potato Crops in Eastern Canada. PLOSONE, 15, e0230888. https://doi.org/10.1371/journal.pone.0230888
[19]
Wang, W., Wu, Y., Zhang, Q., Zheng, H., Yao, X., Zhu, Y., Cao, W. and Cheng, T. (2021) AAVI: A Novel Approach to Estimating Leaf Nitrogen Concentration in Rice from Unmanned Aerial Vehicle Multispectral Imagery at Early and Middle Growth Stages. IEEE Transactions on Geoscience and Remote Sensing, 14, 6716-6728. https://ieeexplore.ieee.org/document/10755182
[20]
Rodier, J. (2009) Water Analysis: Natural Water, Waste Water, Seawater. 9th Edition, Dunod, 100-110. (In French)
[21]
Doorenbos, J. And Pruitt, W.O. (1977) Background and Development of Methods to Predict Reference Crop Evapotranspiration (Eto) Guidelines for Predicting Crop Water Requirements. FAO Irrigation and Drainage Paper No. 24, 144.
[22]
N’cho, H.A., Koffi, K., Konan, S.K., Baï, R., Kouame, I.K. and Kouassi, L.K. (2024) Simulation of the Nitrate Concentrations in Consumed Well Water Using the Error Gradient Backpropagation Neural Network: A Case Study: M’bahiakro (Central-Eastern Ivory Coast). EnvironmentalModeling&Assessment, 29, 855-869. https://doi.org/10.1007/s10666-024-09970-0
[23]
Castellano, G., Fanelli, A.M. and Pelillo, M. (1997) An Iterative Pruning Algorithm for Feedforward Neural Networks. IEEETransactionsonNeuralNetworks, 8, 519-531. https://doi.org/10.1109/72.572092
[24]
Wagh, V.M., Panaskar, D.B., Muley, A.A., Mukate, S.V., Lolage, Y.P. and Aamalawar, M.L. (2016) Prediction of Groundwater Suitability for Irrigation Using Artificial Neural Network Model: A Case Study of Nanded Tehsil, Maharashtra, India. ModelingEarthSystemsandEnvironment, 2, 1-10. https://doi.org/10.1007/s40808-016-0250-3
[25]
Maren, A., Harston, C. and Pap, R. (1990) Handbook of Neural Computing Applications. Academic Press.
[26]
Hecht-Nielsen, R. (1988) Neurocomputing: Picking the Human Brain. IEEESpectrum, 25, 36-41. https://doi.org/10.1109/6.4520
[27]
Artigue, G., Johannet, A., Borrell, V. and Pistre, S. (2012) Flash Flood Forecasting in Poorly Gauged Basins Using Neural Networks: Case Study of the Gardon De Mialet Basin (Southern France). NaturalHazardsandEarthSystemSciences, 12, 3307-3324. https://doi.org/10.5194/nhess-12-3307-2012
[28]
Yan, D., Zhou, Q., Wang, J. and Zhang, N. (2016) Bayesian Regularisation Neural Network Based on Artificial Intelligence Optimisation. InternationalJournalofProductionResearch, 55, 2266-2287. https://doi.org/10.1080/00207543.2016.1237785
[29]
Matthieu, V. (2006) Quantification and Prediction of the Net Mineralization of Soil Nitrogen in Situ, under Various French Pedoclimates and Cropping Systems. Ph.D. Thesis, Institut National polytechnique de toulouse. (in french)
[30]
Fonder, N., Heens, B. and Xanthoulis, D. (2010) Optimising Nitrogen Fertilisation of Irrigated Industrial Vegetable Crops. Biotechnology, Agronomy, Society and Environment, 14, 103-111. (In French)
[31]
FAO (1999) Irrigation in Asia in Figures. FAO Water Report 18, 228.
[32]
Doucet, R. (2006) Le climat et les sols agricoles. Edition, Berger, 443.
[33]
Simard, R.R. and N’dayegamiye, A. (1993) Nitrogen-Mineralization Potential of Meadow Soils. CanadianJournalofSoilScience, 73, 27-38. https://doi.org/10.4141/cjss93-003
[34]
Cambardella, C.A. and Elliott, E.T. (1992) Particulate Soil Organic‐matter Changes across a Grassland Cultivation Sequence. SoilScienceSocietyofAmericaJournal, 56, 777-783. https://doi.org/10.2136/sssaj1992.03615995005600030017x
[35]
Hassink, J. (1997) The Capacity of Soils to Preserve Organic C and N by Their Association with Clay and Silt Particles. PlantandSoil, 191, 77-87. https://doi.org/10.1023/a:1004213929699
[36]
Thomsen, I.K., Olesen, J.E., Schjønning, P., Jensen, B. and Christensen, B.T. (2001) Net Mineralization of Soil N and 15n-Ryegrass Residues in Differently Textured Soils of Similar Mineralogical Composition. SoilBiologyandBiochemistry, 33, 277-285. https://doi.org/10.1016/s0038-0717(00)00138-3
[37]
Schomberg, H.H. and Cabrera, M.L. (2001) Modeling inSitu N Mineralization in Conservation Tillage Fields: Comparison of Two Versions of the CERES Nitrogen Submodel. EcologicalModelling, 145, 1-15. https://doi.org/10.1016/s0304-3800(01)00379-9
[38]
Wen, G., Ma, B., Vanasse, A., Caldwell, C.D., Earl, H.J. and Smith, D.L. (2021) Machine Learning-Based Canola Yield Prediction for Site-Specific Nitrogen Recommendations. NutrientCyclinginAgroecosystems, 121, 241-256. https://doi.org/10.1007/s10705-021-10170-5
[39]
Ma, X., Zhao, Y., Zheng, Y., Wang, L., Zhang, Y., Sun, Y., etal. (2025) Effect of Different Fertilization on Soil Fertility, Biological Activity, and Maize Yield in the Albic Soil Area of China. Plants, 14, Article 810. https://doi.org/10.3390/plants14050810
[40]
Chen, H., Levavasseur, F. and Houot, S. (2024) Substitution of Mineral N Fertilizers with Organic Wastes in Two Long-Term Field Experiments: Dynamics and Drivers of Crop Yields. SoilUseandManagement, 40, e13079. https://doi.org/10.1111/sum.13079
[41]
Zou, Y., Zhang, Y., Cui, J., Gao, J., Guo, L. and Zhang, Q. (2023) Nitrogen Fertilization Application Strategies Improve Yield of the Rice Cultivars with Different Yield Types by Regulating Phytohormones. ScientificReports, 13, Article No. 21803. https://doi.org/10.1038/s41598-023-48491-w
[42]
Yu, X., Keitel, C., Zhang, Y., Wangeci, A.N. and Dijkstra, F.A. (2022) Global Meta-Analysis of Nitrogen Fertilizer Use Efficiency in Rice, Wheat and Maize. Agriculture, Ecosystems&Environment, 338, Article ID: 108089. https://doi.org/10.1016/j.agee.2022.108089
[43]
Blondel, D. (1971) Contribution à l’étude de la dynamique de l’azote en sol sableux (dior) au Sénégal. L’AgronomieTropicale, 26, 1303-1333.
[44]
Rosswall, T. (1980) Nitrogen Cycling in West African Ecosystems. SCOPE/UNEP International Nitrogen Unit, 450.
