Funding Agency:

North Eastern Council for Technology Application and Research (NECTAR)

Objectives of the Project:

1. Enhance community resilience to floods and erosion through awareness programs and capacity building.

2. Provide skill development in flood management and promote advanced technologies like GIS, Remote Sensing, and UAVs.

3. Develop flood-resilient infrastructure and provide science and technology inputs for sustainable flood and erosion management.

4. Raise awareness about the socio-economic impact of floods and erosion.

5. The project targets three flood-prone districts in Assam: Morigaon, Majuli, and Dhubri.

Brief about the Project:

The project focuses on mitigating the devastating impacts of floods and erosion in Assam’s Brahmaputra Valley, a region prone to frequent natural disasters. The project monitors flood-prone areas and provides real-time data for effective flood forecasting and management by employing cutting-edge technologies such as GIS, Remote Sensing, and UAVs. Focused on the districts of Morigaon, Majuli, and Dhubri, where the changing dynamics of the Brahmaputra River exacerbate flooding, the project seeks to create a more resilient future for these vulnerable communities.   

Findings and results:

The project has enhanced our understanding of flood patterns in the target districts using advanced satellite imagery and GIS mapping. Remote Sensing technology has enabled accurate flood prediction and identification of vulnerable infrastructure, leading to improved preparedness. UAVs have facilitated high-resolution mapping of flood-prone zones, contributing to precise flood damage assessments. Capacity-building programs have educated over 500 community members, empowering them to build flood-resistant infrastructure and respond proactively. The project’s technology integration has also led to reduced human and economic losses during floods. The use of GIS and UAVs continues to support informed decision-making for long-term flood mitigation. 

Funding Agency: Mahalanobis National Crop Forecast Centre (MNCFC), Ministry of Agriculture and Farmers Welfare, Government of India

Objectives of the Project

The primary objective of this project was to develop a Gram Panchayat (GP) level crop yield forecast model for three major crops: Mustard, Sorghum, and Maize using Remote Sensing and GIS technologies. The project aimed to accurately forecast crop yields by leveraging high-resolution satellite data, remote sensing parameters, and weather information. A secondary objective was capacity building, with a focus on training interns and students from the North Eastern region of India, providing them with practical skills in data collection, crop classification, and GIS technology. The project engaged several interns and students as part of its capacity-building initiatives

Brief about the Project:

NECTAR was entrusted with the responsibility of developing a crop yield forecasting model at the GP level for 13 districts across India. The project focused on three crops: Mustard, Sorghum, and Maize. The approach utilized high-resolution satellite data from Planet Labs (3m) for Sorghum and Maize, and Sentinel-2 (10m) for Mustard, which was complemented by ground truth data collected by interns and students from the North Eastern region. Remote sensing parameters like NDVI, NDWI, FAPAR, and LAI, along with weather parameters such as rainfall, temperature, and soil moisture, were processed in the NECTAR GIS lab. The collected data was integrated into an AI/ML-based model to generate crop yield forecasts at the GP level

Finding and Results

The crop classification accuracy achieved through the project was impressive, with classification accuracies ranging between 80% and 90%. When the yield estimates for Mustard, Sorghum, and Maize were compared to observed Crop Cutting Experiment (CCE) data, the R² values ranged from 0.82 to 0.88 for all three crops across different districts. These results demonstrated the effectiveness and reliability of the AI/ML-based model in predicting crop yields using remote sensing data. The project’s success was particularly notable considering the limited data availability and the complexity of the task. Additionally, the initiative provided significant livelihood and skill development opportunities for the North Eastern region, enhancing the local expertise in the use of advanced technologies like AI/ML, and GIS in agriculture. Overall, the project contributed substantially to the development of precision agriculture in India and enhanced the capabilities of the regional workforce.