Crop Yield Forecasting Based on Echo State Network Tuned by Crayfish Optimization Algorithm
Nebojša Bačanin, Luka Jovanović, Marko Djordjevic, Aleksandar Petrović, Tamara Živković, Miodrag Živković, Miloš Antonijević
Abstract
The agriculture sector, once reliant only on external inputs for increased yields, faces repercussions of diminished natural systems and significant environmental impact. High-precision agriculture aims to curb excessive usage of fertilizers and pesticides while prioritizing sustainability. Modern technologies can shape decisions toward the betterment of soil health, plant protection, and yield enhancement. Predictive models employing machine learning aid farmers in crop performance estimation, disease detection, soil health assessment, and yield prediction among others. These insights inform field operations, logistics, and contract negotiations. Leveraging machinery data, weather data, and drone imagery using machine learning can help us refine farming practices. Recurrent neural networks (RNN) can aid in various farming challenges like plant stress detection and irrigation. Yet, challenges persist in optimizing hyperparameters, a task we tackled using the nature-inspired crayfish optimization algorithm (COA) adapted to tune echo state networks (ESN) for multivariate time series forecasting of crop yield. This study demonstrates the utility of machine learning in agriculture, enabling yield assessment for improved sustainability.