Predicting Potato Crop Yield with Machine Learning and Deep Learning for Sustainable Agriculture

• DOI: 10.1007/s11540-024-09753-w
• Publication Date: 2024-07-13T03:24:05Z
• Authors: El-Sayed M. El-Ke...; Amel Ali Alhussan; Nima Khodadadi; Seyedali Mirjalili; Marwa M. Eid
• Keywords: 01 natural sciences; 0105 earth and related environmental sciences

Abstract Potatoes are an important crop in the world; they main source of food for a large number people globally and also provide income many people. The true forecasting potato yields is determining factor rational use maximization agricultural practices, responsible management resources, wider regions’ security. latest discoveries machine learning deep new directions to yield prediction models more accurately sparingly. From study, we evaluated different types predictive models, including K-nearest neighbors (KNN), gradient boosting, XGBoost, multilayer perceptron that learning, as well graph neural networks (GNNs), gated recurrent units (GRUs), long short-term memory (LSTM), which popular models. These on basis some performance measures like mean squared error (MSE), root (RMSE), absolute (MAE) know how much predict yields. terminal results show although boosting XGBoost algorithms good at prediction, GNNs LSTMs not only have advantage high accuracy but capture complex spatial temporal patterns data. Gradient resulted MSE 0.03438 R 2 0.49168, while had 0.03583 0.35106. Out all displayed 0.02363 0.51719, excelling overall performance. GRUs were reported be very promising well, with comprehending 0.03177 grabbing 0.03150. findings underscore potential advanced support sustainable practices informed decision-making context farming.