A Novel Clustering Algorithm for Monitoring Paddy Growth Through Satellite Image Processing.

In agriculture, paddy crop monitoring placed a crucial role because it supports food security control. Water shortage, high cost of fertilizers, and soil deterioration were identified as some the difficulties encountered when rice crops through satellite images acquired by remote sensing. This study developed deep learning method-assisted clustering algorithm (DLCA) which helps to improve growth identification process enables transparency agricultural activity. Convolution neural network (CNN) has been utilized identify understand drip irrigation water scarcity for particular crop. The experimental research shows that proposed model is improved in identifying growth, availability, degradation production image process. Overall, findings experiments have carried out, DLCA achieve lower error rate 0.03 accuracy 98.52%, MCC attains 98.43%, F1-score 99.02% compared other popular methods.