A.I. APPROACHES FOR DECISION MAKING IN AGRICULTURAL APPLICATIONS

Abstract

Agricultural policymakers use various types of expert systems to identify agricultural problems and explore their potential solutions. However, in the current scenario, there is no robust system that can be used to collect and analyze information regarding the problems faced by farmers in developing countries on a large scale. Therefore, we are on a continuous quest to develop innovative approaches with the intention of boosting agricultural productivity. For planning agricultural policies, organizing farmers’ training, gaining agricultural product-based market insights, and executing strategic marketing actions, government officials, policymakers, and private organizations need to gain awareness regarding farmers’ problems. However, today, there is a need for such a robust system that can be used to collect and analyze Spatio-temporal information regarding the problems faced by farmers on an extensive scale. In the current scenario, exploring new means to gain accurate information regarding agriculture related problems is the need of the hour. Sustainable development of the national food system must ensure the introduction of adequate food security interventions and policies. However, several high-end technological developments remain unexplored, which can be used to gain explicit information regarding agricultural problems. The decision support systems in need by the policymakers must be able to extract patterns from the farming community to assist farmers accordingly. The systems should be able to process Big data to outline farmers’ problems on an extensive scale to clearly indicate the farmers’ needs. Furthermore, precise spatiotemporal patterns can help decision-makers to introduce adequate policies according to the requirements. There is a need to mine associations/relations between the countrywide agricultural problems. This sequentially will help correlate the issues and can be used in developing recommender systems. Furthermore, the sector requires forecasts of agricultural problems. Therefore, high-end forecasting models are necessary to help decision-makers look into the sector’s future. In addition to such systems, methods that provide information regarding the areas where farmers ask for help corresponding to particular v Abstract problems are also advantageous. Similarly, techniques to deliver in-depth insights regarding the time spans of the problems farmers face regarding the target input problem can be handy. In addition, there is a need for robust agriculture extension-related policies to provide demand-driven extension work based on the extracted insights. In this direction, the presented study outlines the possible mechanisms through which information and communication technology (ICT) with the use of Knowledge Discovery in Databases could facilitate agricultural adoption. The goal of this study is to explore data from a farmers’ helpline center as a new medium to gain hidden insights in terms of association rules regarding the problems faced by Indian farmers. The dataset used in this study is collected from the “Kisan Call Center”, a farmers’ helpline center managed by the Ministry of Agriculture, Government of India. Moreover, in the study, multiple pipelines are developed to deliver various types of novel insights regarding the up-to-date on-goings of the farming community. First, we introduce a pipeline for the extraction of sequential patterns from the farmers’ helpline dataset. For this objective, we propose a new approach that uses association rule mining integrated with a multi-criteria decision-making technique, TOPSIS to extract only the most relevant patterns from the dataset. Later, we perform experiments in order to analyze the output of the proposed framework and verify the discovered knowledge against the validation data. The best experiment generates a rule-set, consisting of 702 association rules, including insights from 25 states of India, with an average confidence value of 73.21% on the validation data. The extracted inference reveals many hidden patterns regarding associations among the farmers’ issues from the remote states of India. Finally, we identify various potential applications of our work and conclude with some possible future developments in the proposed approach. Furthermore, the study introduces a pipeline for development of query-call count forecasting models. Moreover, we take data corresponding to the top-five rice-producing states of India (Uttar Pradesh, Punjab, Bihar, West Bengal, and Andhra Pradesh) as case studies to inspect the performances of the proposed framework with four different forecasting periods (1, 7, 15, and 30-days forecasting). Later, we compare the forecasting potential of four different Machine Learning and Deep Learning-based forecasting techniques, i.e., Support Vector Regression, Multi-layer Perceptron, Long Short-Term Memory Networks, and Gated Recurrent Units using three different performance measures (Mean Squared Error, Mean Absolute Error, and Correlation Coefficient). From the experimental results, we found that the proposed framework is useful for forecasting trends in farmers’ problems, furthermore, we identify various other potential applications of the presented work. In addition, the study proposes a pipeline for obtaining critical dates corresponding to the demand for assistance by the Indian farmers, along with a pipeline for extraction and mapping of geo-locations corresponding to the target agricultural problem. The proposed spatial analysis framework delivers hidden patterns regarding the crop-wise density of farmers calling for help from various regions of the country. In addition, the proposed step-plot concept gives insights into the time span of the problems in the agriculture sector. Besides, the proposed framework explores the potential of high-end forecasting models, including five Deep Learning-based models to predict the topic-wise demand for help (number of query calls) by the producers of the target regions. To elaborate on the utility of the presented work, the article outlines two case studies corresponding to policy recommendations regarding agriculture extension and other related domains.