AgriSense: A Multimodal AI-Driven Decision Support Ecosystem for Climate-Adaptive and Sustainable Agriculture

Nevertheless, the sphere of agriculture is extremely significant to the global economy, and farmers cannot always decide about the crops and determine the fertilizers, organize the irrigation, and diagnose the disease in time due to the low accessibility to the smart decision-support systems. This paper will present AgriSense, a multimodal AI ecosystem, which is to be used to support climate-adaptive and sustainable farming. The proposed system gathers machine learning models that reach crop recommendation, irrigation timetabling and fertilizer optimization based on soil and environmental parameters. The identification of plant diseases through leaf images is implemented through deep learning, which is based on Convolutional Neural Network (CNN) module, and the diagnosis is carried out at an early stage and accurately. Prediction and climate flexibility is enhanced through integration of real time weather data. AgriSense has been designed based on the current web architecture and responsive front-end and scalable back-end that gives the agriSense flexibility of accessibility, multi-lingual environment, and low-connectivity. The combination of smart automation and data-driven insights will assist in increasing the productivity, better resource management, and promote sustainable farming methods with the help of the platform.