Future Farming in India A Playbook for Scaling Artificial Intelligence in Agriculture 2025

Pest and disease control Use case DescriptionHigh-level flowchart of AI value delivery Start-up examples Early pest and disease detectionAI models analyse images of crops to detect early signs of pests or diseases, enabling timely intervention and reducing crop damage. –Images captured via smartphones or drones –AI identifies signs of pests/diseases –Specific issues are diagnosed –Notifications with treatment advice are sent to farmers –Farmers apply remediesPlantix (Germany/India): Case study TartanSense (India): Case study Predictive pest modellingAI predicts pest outbreaks by analysing weather data, crop conditions and historical pest patterns, helping farmers implement preventive measures. –Weather, crop and pest data collected –AI identifies risk factors –Potential outbreaks are forecast –Warnings and preventive advice sent to farmers –Farmers take action to reduce risksClimate Corporation (USA): Case study Wadhwani AI-cotton crop: Case study Integrated pest management (IPM)AI assists in developing IPM strategies by analysing data on pest life cycles, natural predators and environmental conditions to minimize chemical pesticide use. –Data on pests and environment gathered –AI assesses best IPM strategies –Farmers receive guidance on biological controls and minimal pesticide use –Farmers apply recommended practices –AI continues to assess effectiveness and adjusts adviceBayer Crop Science: Case study BioCrop (India) Soil and nutrient management Use case DescriptionHigh-level flowchart of AI value delivery Start-up examples Soil health monitoring with sensorsSensors placed in the soil collect data on moisture, nutrients and pH levels. AI analyses this data to provide recommendations on irrigation and fertilization, helping farmers maintain optimal soil conditions for crop growth. –Soil sensors gather data –AI assesses soil health –AI suggests irrigation and fertilization –Advice is sent to farmers –Farmers adjust practices based on recommendationsCropX (Israel) FarmBee (India): EM3 Agri Services Soil nutrient mappingAI creates detailed maps of soil nutrient levels using sensor data and remote sensing, allowing for precise fertilizer application and improved soil health. –Soil samples and sensor data collected –AI analyses nutrient levels –Detailed nutrient maps are created –Farmers receive guidance on fertilizer application –Precise fertilizer use enhances soil health and crop yieldsKrishi Tantra (India): Case study AI-based soil testingAI algorithms analyse soil images and data to provide instant soil- testing results through mobile apps, reducing the need for laboratory tests and enabling quick decision making. –Farmers capture soil images via app –AI assesses soil properties –Soil test results are provided on the app –Advice on soil-improvement measures is given –Farmers implement suggestions promptlyAgrocares (Netherlands) SoilCares: Case studyAI use cases in agriculture (continued) TABLE 7 Future Farming in India 47