VivaKitLong-Range Monsoon Rainfall Prediction & Drought Risk Estimator
Long-range meteorological rainfall forecasting and agricultural drought classification engine powered by official 115-year India Meteorological Department (IMD) observational data (1901–2015). Engineers multi-scale temporal lag features, rolling moving averages, and subdivisional Long Period Average (LPA) baselines across all 36 Indian meteorological subdivisions. Employs multi-target Random Forest ensembles to predict continuous Southwest Monsoon (Jun–Sep) and total annual precipitation while simultaneously classifying drought and flood risk categories with calibrated probabilities and zero future temporal data leakage.
Secure checkout by Dodo Payments (UPI, cards). Your personalised download link is e-mailed within 24 hours. One purchase covers one project team of up to 4 students. See terms and refunds.
Our honest results
| Total Annual Rainfall R² | 0.900 (Held-out test split 1996–2015, 720 samples) |
| Monsoon (Jun–Sep) Rainfall R² | 0.856 (Held-out test split 1996–2015, 720 samples) |
| Annual Rainfall MAE | 205.3 mm (Across all 36 meteorological subdivisions) |
| Drought Classification | 68.1% accuracy but macro-F1 only 0.33 (classes imbalanced) - honest limitation, good viva discussion point |
Evaluated strictly on held-out 1996–2015 observations from the official IMD meteorological subdivision series (GODL-India). Includes 115-year interactive historical climate explorer, Gradio 6 console, automated pytest suite, and 15 viva voce questions covering atmospheric normals, LPA departures, and hydrological engineering.
What's included
- Readable source codeSmall, commented modules you can explain line by line in your viva.
- Demo appA local web app to show your examiners - runs offline on your laptop.
- Trained model + reference resultsSo you can compare your own runs fairly.
- Learning guide with viva Q&ABackground, design choices explained, limitations and extension ideas.
- One-click setup & testsWindows setup script and tests that prove it works on your PC.
- Dataset download scriptFetches the public data from its original source, with the citation.
Dataset credit
India Meteorological Department (IMD) Monthly Sub-Divisional Rainfall Dataset 1901–2015 via Open Government Data Platform India (data.gov.in, GODL-India).
Academic integrity
We sell code and teaching, not finished projects. You must understand, extend and write up the work yourself, acknowledge the kit and cite the dataset. No ready-made reports.