Machine learning-based optimal crop selection system in smart agriculture
In one sentence. Pairs LSTM-RNN weather forecasting with a Random Forest for crop selection, reporting 5-8% RMSE on temperature and rainfall and 97% crop-selection accuracy.
Abstract
The cultivation of most crops depends upon the regional weather conditions. So, the analysis of the agro-climatic conditions of a zone contributes significantly to deciding the right crop for the right land in the right season to obtain a better yield. Machine learning algorithms facilitate this process to a great extent for better results. In this paper, the authors proposed an ML-based crop selection model based on the weather conditions and soil parameters, collectively. Weather analysis is done using LSTM RNN and the process of crop selection is completed using Random Forest Classifier. This model gives better results for weather prediction in comparison to ANN. With LSTM RNN, the RMSE observed in Min. Temp. prediction is 5.023%, Max. Temp. Prediction is 7.28%, and Rainfall Prediction is 8.24%. In the second phase, the Random Forest Classifier showed 97.235% accuracy for crop selection, 96.437% accuracy in predicting resource dependency, and 97.647 accuracies in giving the appropriate sowing time for the crop. The model construction time taken with a random forest classifier using mentioned data size is 5.34 s. The authors also suggested the future research direction to further improve this work.
Labels
- Topic
- Applications & impacts, Local & station forecasting
- Type
- New model or method
- Method
- RNN / LSTM / ConvLSTM, Classical ML (trees, GP, linear, kernels)
- Time scale
- 6 h–3 days
- Domain
- Local / station
- Data
- Station / in-situ
- Status
- Research
- Identifiers
- DOI:10.1038/s41598-023-42356-y OpenAlex:W4387019227
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.