Novel algorithms for improving agricultural planning and operations using artificial intelligence and game theory

includes bibliographical references and index

PhD; 2023; Computer Science and Automation

This dissertation work is motivated by the critical need to address a perennial global problem, namely, how to mitigate the distress of the small and marginal agricultural farmers in emerging economies. Key reasons behind the low returns, and losses, faced by the farmers include the inherent uncertainty in agriculture, unaffordability of advanced technologies, and lack of access to markets. This dissertation formulates and attempts to, at least partially solve, a few of these problems in agriculture, using artificial intelligence and game theory techniques. Novel solutions are proposed that assist the farmers and the state administration during various stages of the agricultural crop cycle, starting from the pre-sowing and sowing decisions and going right up to the harvesting of the produce. These solutions are: PREPARE (Prediction of Prices in Agriculture), ACRE (Agricultural Crop Recommendation Engine), CROP-S (Crop Planning System), and PROMISE (Procurement Mechanisms for Agricultural Inputs and Services). PREPARE: Accurate prediction of agricultural crop prices is a crucial input for decision-making by various stakeholders in agriculture: farmers, consumers, retailers, wholesalers, and the Government. PREPARE accurately predicts crop prices using historical price information, climatic conditions, soil type, location, and other key determinants. The proposed approach uses graph neural networks (GNNs) in conjunction with a standard convolutional neural network (CNN) model to exploit geospatial dependencies in prices. PREPARE works well with noisy legacy data and produces a performance that is at least 20% better than the state-of-the-art results in the literature. ACRE: A key challenge faced by small and marginal farmers is to determine which crops to grow to maximize their utility. ACRE provides a rigorous, data-driven back-end for designing farmer-friendly mobile applications for assisting farmers in choosing crops. ACRE uses available data such as soil characteristics, weather conditions, and historical yield data, and uses machine learning/deep learning models to compute an estimated utility to the farmer. The main idea of ACRE is to generate several recommendations of portfolios of crops, with a ranking of portfolios based on the Sharpe ratio, a popular risk metric used for evaluating financial investments. CROP-S: To minimize supply-demand mismatch and maximize the profits of the farmers, the Government or state administration can use CROP-S for district level agricultural crop planning. CROP-S uses data about predicted demands, transportation costs, compliance ratios (fraction of farmers who will follow the recommended crop plan), and historical data about yields and prices to arrive at an optimal allocation of crop acreages (number of acres cultivated under each crop) to districts. PROMISE: Procuring agricultural inputs such as seeds, fertilizers, and pesticides, at desired quality levels and at affordable cost, forms a critical component of agricultural input operations. Farmer Producer Organisations (FPOs) or Farmer collectives (FCs), which are cooperative societies of farmers, offer an excellent opportunity for enabling cost-effective procurement of inputs with assured quality to the farmers. They take advantage of economies of scale to ensure that the farmers get good quality inputs at lower prices. The objective of PROMISE is to design sound, explainable mechanisms by which an FC will be able to procure agricultural inputs in bulk and distribute the inputs procured to the individual farmers who are members of the FC. In the methodology proposed, an FC engages qualified suppliers in a competitive, volume discount procurement auction in which the suppliers specify price discounts based on volumes supplied. The desiderata of properties for such an auction include: minimization of the total cost of procurement, incentive compatibility, individual rationality, social welfare maximization, fairness, and satisfying certain practical, business constraints. An auction satisfying all these properties is analytically infeasible. PROMISE uses a novel deep learning based approach to design an auction that satisfies all of these properties, except social welfare maximization, in a regret minimization sense. The suite of AI based and game theory based solutions offered in this thesis, namely PREPARE, CROP-S, ACRE, and PROMISE, constitute a bouquet of innovative approaches towards mitigating the problems faced by small and marginal farmers in emerging economies.