Neural Network-Based Modeling for Precise Potato Yield Prediction Using Soil Parameters
Open Access
Abstract
This study analyses the potential of artificial neural networks (ANN) in accurately predicting potato yields based on 11 parameters characterising the soil environment. Accurate yield forecasting is crucial for optimising potato production, especially in the context of potato processing. Due to the significant impact of soil properties on yield, there is a need for comprehensive predictive models that take these factors into account. The field studies (2021–2024) included an analysis of soil parameters determining potato tuber yield. The developed ANN model was highly accurate, as evidenced by the following indicators: R2 = 0.8227, RMSE = 4.19 t∙ha−1, MAE = 3.35 t∙ha−1, MAPE = 7.34%. Global sensitivity analysis showed that cation exchange capacity (CEC), base saturation percentage (V), and sum of exchangeable bases (S) are key parameters influencing tuber yield. The results indicate that neural networks are effective in modelling complex relationships between soil parameters and potato yield, and that soil properties play a fundamental role in increasing yields and improving potato quality. The approach used may contribute to optimizing the nutrient content of potato tubers intended for French fry production. Future studies should incorporate climate data and micronutrients to enhance the accuracy of predictive models, potentially leading to a 10–15% improvement in yield predictions.Keywords
All Related Versions
This publication has 44 references indexed in Scilit:
- Technologies and strategies for optimizing the potato supply chain: A systematic literature review and some ideas for application in the algerian contextComputers and Electronics in Agriculture, 2025
- Micronutrients and their effects on Horticultural crop quality, productivity and sustainabilityScientia Horticulturae, 2023
- Effects of soil amendments on soil acidity and crop yields in acidic soils: A world-wide meta-analysisJournal of Environmental Management, 2023
- Potassium in plant physiological adaptation to abiotic stressesPlant Physiology and Biochemistry, 2022
- Multi-layer perceptron (MLP) neural network for predicting the modified compaction parameters of coarse-grained and fine-grained soilsInnovative Infrastructure Solutions, 2021
- Artificial neural network model in predicting yield of mechanically transplanted rice from transplanting parameters in BangladeshJournal of Agriculture and Food Research, 2021
- Agro-climatic conditions of the Southern Federal District of Russia in the context of climate changeTheoretical and Applied Climatology, 2021
- Short term soil moisture forecasts for potato crop farming: A machine learning approachComputers and Electronics in Agriculture, 2021
- Determination of base saturation percentage in agricultural soils via portable X-ray fluorescence spectrometerGeoderma, 2019
- Soil porosity and water infiltration as influenced by tillage methodsSoil and Tillage Research, 2006