Interplay of Remote Sensing and Artificial Intelligence in Open Agricultural Land Monitoring

As a prominent global player in rice production, the Philippines has consistently upheld its commitment to ensuring food security and meeting the demands of its population. This was highly evident in the year 2021 when the nation achieved a milestone by yielding a harvest of 19.96 million metric tons of rice. However, due to its geographical location in Southeast Asia and its influence on global warming, the country is highly susceptible to the devastating effects of tropical cyclones. Climate change, particularly the rise in global temperatures, makes oceans heat up more. This leads to an increase in the frequency and intensity of weather events that pose a significant threat to the agricultural sector and profoundly impact the livelihood of farmers who heavily rely on crops. Several studies collectively aimed to assess the impact of crop losses on agricultural fields, particularly areas prone to natural disasters. These studies utilized diverse methodologies that comprehensively evaluated the impact of these disasters on crop fields and the economic losses in the area, therefore providing significant insights into environmental factors and agricultural productivity in farming areas. The methodologies employed in these studies focused on improving crop prediction through data analysis techniques. Machine learning approaches like Support Vector Machines and Decision Tree algorithms were utilized in enhancing the efficiency of crop management. Data collection was gathered from diverse sources like government websites. While technology-driven approaches like data logging, satellite imagery, and machine learning were used to locate and map crop production stages.