IoT Agriculture 2024 - Precision Farming Sensor Dataset

Dataset Description

The IoT Agriculture 2024 dataset provides real-world sensor measurements from precision farming deployments, enabling research in smart agriculture, crop optimization, and automated farming systems. Published on Kaggle in April 2024, it captures the complete agricultural IoT ecosystem.

Sensor Categories

Soil Analysis Sensors

• Soil Moisture (%): Volumetric water content for irrigation scheduling
• Soil Temperature (°C): Underground thermal conditions affecting root growth
• Soil pH: Acidity/alkalinity levels determining nutrient availability
• Soil EC (mS/cm): Electrical conductivity measuring salinity and nutrient concentration

Environmental Monitoring

• Air Temperature (°C): Ambient conditions for crop stress analysis
• Air Humidity (%): Relative humidity affecting disease risk
• Light Intensity (Lux): Solar radiation for photosynthesis modeling
• Rainfall (mm): Precipitation data for water budget calculations

Crop Parameters

• Crop Type: Different plant species with varying requirements
• Growth Stage: Phenological phases (germination, vegetative, flowering, fruiting)
• Crop Health Index: Normalized vegetation index or similar health metrics

Decision Support Features

The dataset includes actionable recommendations derived from sensor data:

• Irrigation Recommendation: Binary or multi-level irrigation scheduling (no irrigation, light, moderate, heavy)
• Fertilizer Type: NPK ratios and micronutrient recommendations
• Fertilizer Amount (kg/ha): Precise application rates
• Pest Risk Level: Environmental-based disease and pest pressure predictions

Agricultural Research Applications

• Precision Irrigation: ML models predicting optimal irrigation timing and volume based on soil moisture trends and weather forecasts
• Yield Prediction: Regression models correlating sensor data with final crop productivity
• Resource Optimization: Minimize water and fertilizer usage while maintaining yields
• Disease Prevention: Early warning systems using humidity, temperature, and rainfall patterns
• Climate Adaptation: Study crop responses to varying environmental conditions for resilient agriculture

Machine Learning Tasks

• Classification of irrigation needs based on multi-sensor inputs
• Time-series forecasting of soil moisture depletion rates
• Clustering to identify field zones with similar characteristics
• Recommendation systems for fertilizer type and dosage
• Anomaly detection for sensor malfunctions or extreme events