Machine Learning-Driven Remote Sensing Applications for Agriculture in India—A Systematic Review

Abstract

In India, agriculture serves as the backbone of the economy, and is a primary source of employment. Despite the setbacks caused by the COVID-19 pandemic, the agriculture and allied sectors in India exhibited resilience, registered a growth of 3.4% during 2020–2121, even as the overall economic growth declined by 7.2% during the same period. The improvement of the agriculture sector holds paramount importance in sustaining the increasing population and safeguarding food security. Consequently, researchers worldwide have been concentrating on digitally transforming agriculture by leveraging advanced technologies to establish smart, sustainable, and lucrative farming systems. The advancement in remote sensing (RS) and machine learning (ML) has proven beneficial for farmers and policymakers in minimizing crop losses and optimizing resource utilization through valuable crop insights. In this paper, we present a comprehensive review of studies dedicated to the application of RS and ML in addressing agriculture-related challenges in India. We conducted a systematic literature review following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines and evaluated research articles published from 2015 to 2022. The objective of this study is to shed light on the application of both RS and ML technique across key agricultural domains, encompassing “crop management”, “soil management”, and “water management, ultimately leading to their improvement. This study primarily focuses on assessing the current status of using intelligent geospatial data analytics in Indian agriculture. Majority of the studies were carried out in the crop management category, where the deployment of various RS sensors led yielded substantial improvements in agricultural monitoring. The integration of remote sensing technology and machine learning techniques can enable an intelligent approach to agricultural monitoring, thereby providing valuable recommendations and insights for effective agricultural management.

Geospatial Technology for Sustainable Agricultural Water Management in India—A Systematic Review

“…Our primary objective was to explore research studies pertaining to the integration of RS and GIS technologies in the context of agricultural water management. The PRISMA framework consists of four distinct stages-identification, screening, eligibility, and inclusion [5]. Three research questions are the primary source of this review article: (1) What specific agricultural water management challenges in India are addressed through geospatial technology?…”

“…This is especially critical in areas where irrigation is indispensable for achieving the desired crop quality and yield. To enhance irrigation management and scheduling, it is essential to have a precise understanding of the quantity and timing of the water supply, which can be assessed through an accurate spatial evaluation of plant water stress [4,5]. Efficient agricultural water management practices are essential to expand irrigation coverage in India.…”

“…The acquisition of precise spatio-temporal meteorological and crop data is indispensable for precise analysis, forecasting, and agricultural planning. It plays a vital role in making informed decisions concerning irrigation scheduling, crop stress management, disaster readiness, and the preservation of natural resources and ecosystems in diverse regions [5]. The overarching objective of sustainable agriculture is to achieve a harmonious balance between available land resources and crop requirements, with a strong emphasis on optimizing resource usage to ensure sustained productivity over an extended period.…”

An Overview of Machine Learning Applications on Plant Phenotyping, with a Focus on Sunflower

“…Semi-supervised learning is a combination of the previous ones because there are labelled and non-labelled data. Lastly, reinforcement learning is used for real-time decision making based on the best actions that can lead to a more positive outcome [41,42].…”

“…Table 1. For an immediate and intuitive understanding, each row of the table corresponds to a learning type, its possible use, and the algorithms available, adapted from [42,43]. Given the versatility of the use of ML techniques, the main algorithms used in agriculture have been reported.…”