An Integrated Real Time IoT System for Soil Monitoring and Deep Learning Based Plant Health Assessment

Abstract-Agriculture plays an important role in economic development and food production.Effective agricultural monitoring requires information about soil conditions andplant health. Conventional monitoring practices may not provide integratedinformation about soil moisture, nutrient levels, and visible plant health. Advancedtechnologies such as the Internet of Things (IoT) and deep learning (DL) cansupport intelligent agricultural monitoring. In this paper an integrated IoT and DLbased framework is proposed for agricultural soil monitoring and plant leaf healthassessment. Here a capacitive soil moisture sensor and RS485 based NPK sensorare interfaced with an ESP32 microcontroller to measure soil moisture andnitrogen, phosphorus, and potassium concentrations. The acquired measurementsare transmitted to a Firebase cloud database via Wi-Fi. Finally, it displayed on aweb-based dashboard for real time monitoring of soil conditions. In parallel, theproposed Chry-CDNet model analyses chrysanthemum leaf images. It classifiesplant health into two categories: healthy and diseased. The model achievedclassification accuracy of:96.67±0.11%. This result demonstrates its effectivenessin assessing plant health using leaf images. The framework combines sensorderived soil information with visual plant assessment to provide a comprehensiveview of chrysanthemum cultivation conditions. The system supports data drivencrop monitoring and promotes precision floriculture.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-14
DOI
https://doi.org/10.5281/zenodo.24245969
Primary Topic
Smart Agriculture and AI
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

An Integrated Real Time IoT System for Soil Monitoring and Deep Learning Based Plant Health Assessment

Moumita Sarkar
Zenodo (CERN European Organization for Nuclear Research)
Smart Agriculture and AI
article

An Integrated Real Time IoT System for Soil Monitoring and Deep Learning Based Plant Health Assessment

Moumita Sarkar
article en

Abstract

Abstract-Agriculture plays an important role in economic development and food production.Effective agricultural monitoring requires information about soil conditions andplant health. Conventional monitoring practices may not provide integratedinformation about soil moisture, nutrient levels, and visible plant health. Advancedtechnologies such as the Internet of Things (IoT) and deep learning (DL) cansupport intelligent agricultural monitoring. In this paper an integrated IoT and DLbased framework is proposed for agricultural soil monitoring and plant leaf healthassessment. Here a capacitive soil moisture sensor and RS485 based NPK sensorare interfaced with an ESP32 microcontroller to measure soil moisture andnitrogen, phosphorus, and potassium concentrations. The acquired measurementsare transmitted to a Firebase cloud database via Wi-Fi. Finally, it displayed on aweb-based dashboard for real time monitoring of soil conditions. In parallel, theproposed Chry-CDNet model analyses chrysanthemum leaf images. It classifiesplant health into two categories: healthy and diseased. The model achievedclassification accuracy of:96.67±0.11%. This result demonstrates its effectivenessin assessing plant health using leaf images. The framework combines sensorderived soil information with visual plant assessment to provide a comprehensiveview of chrysanthemum cultivation conditions. The system supports data drivencrop monitoring and promotes precision floriculture.

Zenodo (CERN European Organization for Nuclear Research)
Smart Agriculture and AI
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon