EcoFarm for Integrated Multi-Trophic Aquaculture: An Operational Manual

Abstract

Farm ponds serve as critical livelihood assets for smallholder farmers in socioeconomically vulnerable regions such as Mandla district, Madhya Pradesh; however, suboptimal water quality management, limited scientific guidance, and low primary productivity continue to constrain aquaculture performance. Integrated Multi-Trophic Aquaculture (IMTA) offers a resilience-enhancing model by promoting nutrient recycling, ecosystem balance, and diversification of outputs. However, IMTA adoption at scale requires timely ecological monitoring and informed decision-making, an ongoing challenge for resource-constrained farmers. To address this gap, we developed EcoFarm, a mobile application equipped with advanced computational analytics to support precision management of IMTA systems. The application integrates machine learning algorithms for disease risk prediction and ecological performance scoring using key water quality parameters, plankton indices, stocking ratios and production. A Multi-Criteria Decision-Making (MCDM) framework is embedded to evaluate resource efficiency, species-wise productivity, and nutrient utilisation performance, enabling the identification of high-performing farmers and context-specific corrective interventions. EcoFarm simultaneously supports bottom-up data acquisition, automated spatiotemporal trend analysis, and expert-informed advisory services and recommendations. Designed with lightweight architecture and multi-lingual accessibility, the tool ensures usability among digitally marginalised communities. Results demonstrate that integrating IMTA knowledge with machine-learning-enabled decision support significantly enhances environmental stability, reduces disease incidences, and improves the economic viability of farm-pond aquaculture. EcoFarm thus represents a scalable digital decision-support ecosystem for strengthening multifunctional landscape strategies and accelerating sustainable aquaculture transitions in rural India.