A Real-Time Precision Monitoring And Detection System For Rice Plant Diseases Using Machine Learning Approach

Abstract

Crop disease results in financial loss for farmers. Crop losses are mostly caused by diseases, pests, weeds, and animals. These elements have a significant detrimental impact on global agricultural production, which can range from 20% to 40%, according to an IRJET study. Traditionally, crop diseases have been identified by observing changes in leaf texture, colours, and shape, however this approach is ineffectual. In turn, it provides farmers with access to knowledgeable agriculturists in every continent for the detection of crop diseases on big farms. However, it appears that this strategy requires more time and is more cost-effective.

Farmers' traditional approaches for crop disease prediction fall short in a number of crucial areas when compared to modern systems for automated crop disease detection and categorization. On large farms, the amount and quality of agricultural products will decrease if a farmer does not take the disease into account. Smart agriculture is a smart digital method for farmers because it provides continuous crop disease monitoring, especially in remote agricultural fields.

When a specific causal agent consistently impacts a crop, it can be frequently affected by illness, resulting in irregularities in its physiological process. The crop's normal development, function, and other processes are also in jeopardy due to these aberrations. Modifications to its physiological and biochemical processes cause the causative agent to manifest as diseases and signs in plants.