Optimization of irrigation and fertigation in smart agriculture: An IoT-based micro-services framework

Abstract

Efficient management of water and fertilizer resources is crucial for achieving sustainability and productivity in agriculture. This paper presents an AI-powered microservices solution that optimizes irrigation and fertigation practices. The proposed system integrates IoT nodes for real-time data collection on environmental conditions, soil moisture levels, and nutrient crop needs. Fertigation and irrigation decision-making are modeled as a data-driven sequential decision problem. At each decision stage, real-time data serve as input to an AI planning model aimed at satisfying nutrient and water demands while minimizing water and fertilizer waste. The system allows supervision by the farmer through a mobile app and a Digital Twin, enabling the design of crop planting layouts and providing detailed information on real-time decisions implemented in the field, as well as water and fertilizer consumption. The proposed solution manages diverse crop species with distinct water and nutrient requirements. Efficient data exchange is facilitated through a push-pull communication paradigm between the IoT nodes and cloud services. This approach offers several benefits, including greater control over data flow, energy savings, and increased flexibility in resource management. • A framework for an IoT-based smart aimed at fine-tuning the supply of individual macronutrients and water to each distribution channel. • We model fertigation and irrigation decision-making as a data-driven sequential decision problem. At each decision stage, real-time data is used as input to an Integer Linear Programming (ILP) model designed to meet nutrient and water demands while minimizing resource waste. • A comprehensive evaluation of the proposed framework was conducted in greenhouses with various horticultural species and growing methods, including both soil and soilless techniques.

Topics & Concepts