AARSSSMAP
Visual Abstract Image
Objectives
- To Study the effect of Pesticides and Chemical Fertilizers on Soil Fertility and Quality.
- To predict the long-term effect of using different Pesticides and Chemical Fertilizers on soil using Machine and Deep learning models.
- To Develop a LLM based system that can recommend the bio-fertilizers and organic farming crops based on different factors like soil nutrient values, local weather and water availability to increase Gross Agricultural Income.
Issues Involved
- Degradation of Soil Fertility
Excessive and unregulated use of chemical fertilizers and pesticides has led to nutrient imbalance, reduced organic matter, and decline in soil microbial activity, ultimately lowering soil productivity
- Environmental and Ecological Impact
Chemical residues from agrochemicals contaminate soil and water resources, affecting biodiversity, groundwater quality, and long-term environmental sustainability
- Lack of Data-Driven Decision Support for Farmers
Most farmers rely on traditional practices or generic recommendations, lacking access to personalized, data-driven insights based on soil health, weather conditions, and water availability
- Difficulty in Predicting Long-Term Soil Health
The long-term impacts of continuous pesticide and fertilizer usage are complex and nonlinear, making it challenging to forecast soil degradation without advanced AI/ML and time-series prediction models
- Low Adoption of Sustainable and Organic Practices
Limited awareness, insufficient guidance, and uncertainty about economic returns discourage farmers from adopting bio-fertilizers and organic farming practices
- Integration Challenges of Multisource Agricultural Data
Combining heterogeneous data sources such as soil parameters, weather patterns, crop yield records, and IoT sensor data into a unified, reliable system remains a technical challenge
- Need to Enhance Farmer Income Sustainably
Increasing Gross Agricultural Income while maintaining soil health and reducing chemical dependency is a critical challenge that requires intelligent, context-aware recommendation systems
Team Lead
Dr. G. Paliwal
gaurav.paliwal@nmims.edu
Team Members
Dr. N. Asthana
nidhi.asthana@nmims.edu
