Assessing the Efficacy of IoT-driven Machine Learning Models in Enhancing Chili Crop Growth and Yield Quality

Abstract

This study analyses the plant growth and yield parameters in drip-irrigated and furrow irrigated chili fields in the Guntur region during Kharif 2021. As a part of the DST-SEED project, 48 farmers' chili crops were selected amongst 21 clusters to collect data on soil characteristics, fruits of each plant, their height, fruit length, and fruit yield. The present comparative study purposes to establish the growth and quality of chili fields in the selected drip-irrigated areas. The study's findings show that the approach of drip irrigation integrated with the Internet of Things (IoT) devices excelled in all parameters studied over the furrow irrigation method. The maximum and minimum plant heights in a drip-irrigated farmer's field were 102.3 and 77.46 cm, respectively. While furrow irrigated, farmer's fields produced plant heights of 93.3 and 70.3 cm, respectively. The maximum and minimum number of plant-1 fruits and fruit lengths are 110 and 81.5, 8.1, and 5.9 cm were recorded in the drip-irrigated farmer's field integrated with IoT devices. IoT devices were placed to control the water flow smartly through a mobile app. At the same time, furrow-irrigated farmer's fields could produce the lowest yield of fruits in plant-1; the fruit lengths (cm) are 94.57 and 70.21, 6.7 and 4.7 cm, respectively. The current research recommends that agricultural communities use drip irrigation integrated with IoT devices instead of the old conventional flooding techniques, assess the nutrient state of their soil, implement the indicated logical nutrient management practices, smart motor control, and plant high-yielding varieties or hybrids. This research underscores the importance of adopting modern agricultural techniques, including drip irrigation integrated with IoT devices and machine learning-based predictive models, for enhancing chili yield growth.