Upload 5 files

Readme.md

@@ -0,0 +1,103 @@
+#  GHI Prediction — Solar Radiation Forecasting System
+
+This interactive demo presents a production-grade **machine learning system** for predicting **Global Horizontal Irradiance (GHI)** using real-world weather data collected from weather stations across **Saudi Arabia**.
+
+The model enables fast and accurate solar radiation forecasting, supporting applications in **solar energy planning, grid optimization, and sustainable infrastructure development**.
+
+---
+
+##  Input Features & Valid Ranges
+
+All inputs are validated using real data bounds to ensure reliable predictions:
+
+| Feature | Valid Range |
+|-------|------------|
+Air Temperature (°C) | 8.10 – 39.70 |
+Air Temperature Uncertainty (°C) | 0.50 – 0.60 |
+Wind Direction (°N) | 0 – 359 |
+Wind Direction Uncertainty (°N) | 0.0 – 4.80 |
+Wind Speed at 3m (m/s) | 0.0 – 7.80 |
+Wind Speed Uncertainty (m/s) | 0.0 – 0.10 |
+Wind Speed Std Dev (m/s) | 0.0 – 4.50 |
+DHI (Wh/m²) | 865.8 – 6394.6 |
+DHI Uncertainty (Wh/m²) | 37.3 – 1344.8 |
+Standard Deviation DHI (Wh/m²) | 148.3 – 1649.6 |
+DNI (Wh/m²) | 0.3 – 9517.0 |
+DNI Uncertainty (Wh/m²) | 0.2 – 2115.8 |
+Standard Deviation DNI (Wh/m²) | 0.4 – 3282.2 |
+GHI Uncertainty (Wh/m²) | 98.4 – 5249.6 |
+Standard Deviation GHI (Wh/m²) | 117.6 – 1720.7 |
+Peak Wind Speed at 3m (m/s) | 0.0 – 40.5 |
+Peak Wind Speed Uncertainty (m/s) | 0.0 – 0.20 |
+Relative Humidity (%) | 8.3 – 95.9 |
+Relative Humidity Uncertainty (%) | 2.8 – 3.7 |
+Barometric Pressure (hPa) | 831.3 – 1019.7 |
+Barometric Pressure Uncertainty (hPa) | 4.1 – 6.2 |
+
+---
+
+##  Model & Training Summary
+
+Multiple machine learning models were trained and evaluated:
+
+- Linear Regression **(Deployed Model)**
+- Random Forest
+- Decision Tree
+- KNN
+- SVR
+- XGBoost
+- Artificial Neural Network
+- Histogram Gradient Boosting
+
+###  Final Model Selection Strategy
+
+The final deployed model — **Linear Regression** — was selected using an automated ranking system that balances:
+
+- **Prediction accuracy** (RMSE, R²)
+- **Inference latency** (real-time performance)
+
+This approach ensures both **high accuracy and fast response** for real-world deployment.
+
+###  Best Model Performance
+
+| Model | MAE | RMSE | R² | Training Time |
+|------|------|------|------|------|
+Linear Regression | 135.94 | 193.74 | 0.97 | 0.01s |
+Histogram Gradient Boosting | 140.58 | 192.11 | 0.98 | 0.83s |
+XGBoost | 148.37 | 198.05 | 0.97 | 2.73s |
+ANN | 154.4 | 241.22 | 0.96 | 10.6s |
+
+---
+
+##  Experiment Tracking
+
+All experiments, comparisons, and model selection were tracked using **Weights & Biases** with full reproducibility and visualization.
+
+🔗 W&B Dashboard:  
+https://wandb.ai/nishnarudkar-d-y-patil-university/solar-radiation-prediction
+
+---
+
+##  Full Project Ecosystem
+
+- 🖥️ **Live Web Application:**  
+  https://solar-radiation-prediction-using-saudi.onrender.com
+- 💻 **Source Code (GitHub):**  
+  https://github.com/nishnarudkar/Solar-Radiation-Prediction-using-Saudi-Arabia-Dataset
+- 🧑‍🔬 **AWS Builder Center Article:**  
+  https://builder.aws.com/content/36qXvwTipuNwbZMUPf3hQ7n2IS0/from-experiment-tracking-to-automated-model-selection-a-solar-radiation-prediction-pipeline
+- 📰 **Medium Article:**  
+  https://medium.com/@nishnarudkar/from-experiment-tracking-to-automated-model-selection-a-practical-ml-workflow-cf193d1b1098
+
+---
+
+##  Team
+
+- **Nishant Narudkar**
+- Maitreya Pawar  
+- Vatsal Parmar  
+- Aamir Sarang  
+
+---
+
+This Hugging Face Space demonstrates the final trained model with validated real-world constraints and a clean interactive interface for public experimentation.

app.py

@@ -0,0 +1,47 @@
+import gradio as gr
+import joblib
+import numpy as np
+
+# Load trained artifacts
+model = joblib.load("linear_regression_model.pkl")
+scaler = joblib.load("linear_regression_standard_scaler.pkl")  # remove if you didn't use scaling
+
+def predict(*inputs):
+    X = np.array(inputs).reshape(1, -1)
+    X = scaler.transform(X)   # remove if no scaling
+    prediction = model.predict(X)
+    return round(float(prediction[0]), 3)
+
+inputs = [
+    gr.Number(label="Air Temperature (°C)", minimum=8.10, maximum=39.70, value=25, info="Range: 8.10 - 39.70 °C"),
+    gr.Number(label="Air Temp Uncertainty (°C)", minimum=0.50, maximum=0.60, value=0.55, info="Range: 0.50 - 0.60 °C"),
+    gr.Number(label="Wind Direction (°N)", minimum=0.0, maximum=359.0, value=180, info="Range: 0 - 359 °N"),
+    gr.Number(label="Wind Direction Uncertainty (°N)", minimum=0.0, maximum=4.80, value=1, info="Range: 0.0 - 4.80 °N"),
+    gr.Number(label="Wind Speed at 3m (m/s)", minimum=0.0, maximum=7.80, value=2, info="Range: 0.0 - 7.80 m/s"),
+    gr.Number(label="Wind Speed Uncertainty (m/s)", minimum=0.0, maximum=0.10, value=0.05, info="Range: 0.0 - 0.10 m/s"),
+    gr.Number(label="Wind Speed Std Dev (m/s)", minimum=0.0, maximum=4.50, value=1, info="Range: 0.0 - 4.50 m/s"),
+    gr.Number(label="DHI (Wh/m²)", minimum=865.8, maximum=6394.6, value=2000, info="Range: 865.8 - 6394.6 Wh/m²"),
+    gr.Number(label="DHI Uncertainty (Wh/m²)", minimum=37.3, maximum=1344.8, value=200, info="Range: 37.3 - 1344.8 Wh/m²"),
+    gr.Number(label="Standard Deviation DHI (Wh/m²)", minimum=148.3, maximum=1649.6, value=300, info="Range: 148.3 - 1649.6 Wh/m²"),
+    gr.Number(label="DNI (Wh/m²)", minimum=0.3, maximum=9517.0, value=3000, info="Range: 0.3 - 9517.0 Wh/m²"),
+    gr.Number(label="DNI Uncertainty (Wh/m²)", minimum=0.2, maximum=2115.8, value=300, info="Range: 0.2 - 2115.8 Wh/m²"),
+    gr.Number(label="Standard Deviation DNI (Wh/m²)", minimum=0.4, maximum=3282.2, value=400, info="Range: 0.4 - 3282.2 Wh/m²"),
+    gr.Number(label="GHI Uncertainty (Wh/m²)", minimum=98.4, maximum=5249.6, value=500, info="Range: 98.4 - 5249.6 Wh/m²"),
+    gr.Number(label="Standard Deviation GHI (Wh/m²)", minimum=117.6, maximum=1720.7, value=300, info="Range: 117.6 - 1720.7 Wh/m²"),
+    gr.Number(label="Peak Wind Speed at 3m (m/s)", minimum=0.0, maximum=40.5, value=5, info="Range: 0.0 - 40.5 m/s"),
+    gr.Number(label="Peak Wind Speed Uncertainty (m/s)", minimum=0.0, maximum=0.20, value=0.05, info="Range: 0.0 - 0.20 m/s"),
+    gr.Number(label="Relative Humidity (%)", minimum=8.3, maximum=95.9, value=50, info="Range: 8.3 - 95.9 %"),
+    gr.Number(label="Relative Humidity Uncertainty (%)", minimum=2.8, maximum=3.7, value=3.2, info="Range: 2.8 - 3.7 %"),
+    gr.Number(label="Barometric Pressure (hPa)", minimum=831.3, maximum=1019.7, value=950, info="Range: 831.3 - 1019.7 hPa"),
+    gr.Number(label="Barometric Pressure Uncertainty (hPa)", minimum=4.1, maximum=6.2, value=5, info="Range: 4.1 - 6.2 hPa")
+]
+
+app = gr.Interface(
+    fn=predict,
+    inputs=inputs,
+    outputs=gr.Number(label="Predicted GHI (Wh/m²)"),
+    title="🌞 GHI Prediction System",
+    description="Real-time Global Horizontal Irradiance prediction using Saudi Arabia weather data."
+)
+
+app.launch()

linear_regression_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8908ce076ffa8fe0b3fbad4bc844915b8bca0b53d2246a562d4d366b29f81594
+size 1905

linear_regression_standard_scaler.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:912e75055e8c50191fec7eced08e7585a28c1e99c012fa1e878c09c0a11c4ede
+size 2143

requirements.txt

@@ -0,0 +1,5 @@
+gradio
+scikit-learn
+numpy
+joblib
+pandas