ABSTRACT
Over several years, agriculture is a catalyst for formation and improvement of human society. In today’s era of glocalization, agriculture is still playing a central role in social, cultural, and financial development of a nation. India’s 75% rural population depends on the farming sector taking into consideration of everyone’s well-being, and cultivation accounts for 17% of India’s GDP. In recent decades, the unpredictability of the environmental conditions and crop-related diseases has been posing a serious challenge to the full efficiency and productivity of the agriculture sector. This review concentrates mostly on the classification and prognosis of diseases by using a deep learning (DL) dataset collection of pictures, which promotes efficiency via proper detection of the occurrence of diseases and problems. Throughout this segment, a Self-Predictable Crop Yield Platform (SCYP) using DL to estimate grain yield and detect crop diseases would be addressed that not only collects climate records (temperature, humidity, sunlight, precipitation, and many others), using Convolutional Neural Network (CNN), but also forecasts agricultural productivity based primarily on elements like weather through Artificial Neural Network (ANN). In addition, multiple scientific evaluations and an analysis of the history of crop stress determining technology are addressed in this section.
