Smart Agriculture Plant Health Monitoring - IoT Sensor Dataset

Dataset Description

This dataset represents real-world deployment of IoT sensors for precision agriculture, developed at La Trobe University in Australia. It provides comprehensive environmental and soil monitoring data essential for smart farming applications and plant health optimization.

Sensor Suite - 9 Parameters

The dataset captures timestamped readings from multiple sensor types deployed in agricultural fields:

Environmental Monitoring

• Environmental Temperature (°C): Ambient air temperature readings
• Environmental Humidity (%): Relative humidity measurements
• Light Intensity (Lux): Solar radiation and daylight levels for photosynthesis analysis
• Solar Panel Battery Voltage (V): Power system monitoring for IoT device sustainability

Soil Analysis

• Soil Moisture (%): Volumetric water content critical for irrigation scheduling
• Soil Temperature (°C): Underground temperature affecting root development
• Soil Humidity (%): Additional moisture characterization
• Soil pH: Acidity/alkalinity levels affecting nutrient availability
• Water TDS (ppm): Total Dissolved Solids measuring water quality for irrigation

Hardware Architecture

The system employs industry-standard components for reliable data collection:

• Microcontroller: Arduino platform for sensor integration and data processing
• Connectivity: ESP8266 Wi-Fi module enabling wireless cloud transmission
• Cloud Platform: ThingSpeak for real-time data visualization and storage
• Protocol: HTTP requests for secure data transmission
• Power: Solar panel with battery backup for sustainable operation

Data Format and Structure

The dataset is provided in XLSX format with each column representing a sensor parameter and each row containing timestamped readings. The temporal resolution enables detection of daily patterns, growth cycles, and response to weather events.

Agricultural Applications

• Precision Irrigation: Optimize water usage based on real-time soil moisture
• Crop Health Prediction: ML models correlating environmental conditions with plant stress
• Disease Prevention: Early detection of conditions favoring pathogen development
• Yield Optimization: Identify optimal growing conditions for maximum productivity
• Resource Management: Reduce fertilizer and water waste through data-driven decisions
• Climate Adaptation: Study plant responses to varying environmental conditions

Machine Learning Use Cases

• Time-series forecasting of soil moisture for irrigation scheduling
• Classification of optimal growing conditions
• Anomaly detection for sensor malfunction or pest infestations
• Regression models predicting crop yield from environmental factors
• Clustering analysis to identify microclimate zones within fields

Research Value

This dataset bridges the gap between laboratory simulations and real agricultural deployments. The integration of both environmental and soil parameters provides holistic insight into the complex interactions affecting plant health in precision agriculture systems.