Bhopal AgriTech IoT Dataset for Predictive Irrigation

This dataset contains time-stamped IoT sensor readings related to agricultural irrigation including soil moisture, temperature, humidity, rainfall, sunlight exposure, and other environmental variables relevant to crop water management. The dataset has been processed through a structured exploratory data analysis workflow including duplicate removal, timestamp normalization, sensor value range validation, and missing value treatment. Statistical anomaly detection techniques were applied to identify unrealistic sensor spikes. The final dataset is exported in a clean CSV format optimized for predictive modeling, irrigation forecasting, and smart agriculture analytics.

Data Quality

The dataset is organized in a normalized tabular format with consistent column naming and validated numeric data types. Duplicate sensor readings have been removed to preserve time-series integrity. Numeric sensor values such as soil moisture, temperature, and humidity have undergone range validation to eliminate physically unrealistic measurements. Timestamps were standardized to ensure chronological consistency. The dataset is analytics-ready and supports regression modeling, classification of irrigation needs, and IoT-driven agricultural research.

Use Cases

This dataset can be used for predictive irrigation modeling, smart farming dashboard development, and water management optimization. Data scientists can build machine learning models to predict irrigation requirements based on environmental sensor data. Agricultural researchers can analyze the relationship between soil conditions and crop water demand. Policymakers and agri-tech innovators can use it for precision farming research and resource efficiency planning. The dataset also supports academic research in agricultural IoT and climate-resilient farming.

Limitations

The dataset is community-sourced and reflects sensor data collected in a specific geographic region (Bhopal), which may limit its generalizability to other climatic zones. It may not capture all environmental variables affecting irrigation requirements. Sensor accuracy depends on the original IoT hardware setup. The dataset is intended for research and analytical purposes and should not replace official agronomic recommendations.

Methodology

The dataset was prepared using a structured validation and normalization framework including schema standardization, duplicate removal, sensor value range validation, missing value treatment, and timestamp normalization. Statistical anomaly detection techniques were applied to identify unrealistic sensor readings. Logical consistency checks were performed across related environmental variables. The final dataset was exported in UTF-8 encoded CSV format to ensure compatibility with IoT analytics tools, machine learning libraries, and business intelligence platforms.