AI Water Intelligence Dashboard — Idriss I Dam, Morocco
# 💧 Idriss I Dam — AI Water Intelligence Dashboard
> **AI Systems for Optimal Control and Management of Climate Impact on Water Resources**
> Case Study: Idriss I Dam, Sebou Basin, Morocco
> Authors: EL MANSOURI Aya · EL RHORBA Aya ·
---
## Table of Contents
1. What This App Does
3. Requirements
4. Installation
5. Running the App
6. File Descriptions
7. How to Use — Step by Step
8. Data Format
9. Model Files
10. Deploying Online (Streamlit Cloud)
11. Troubleshooting
---
## What This App Does
This is a 6-page Streamlit dashboard that:
- **Monitors** the Idriss I Dam in real time using satellite altimetry data (DAHITI) merged with NASA POWER climate data
- **Trains** 6 AI models (Ridge, Random Forest, XGBoost, LightGBM, LSTM, GRU) + an Ensemble on your data
- **Forecasts** dam volume 1 day to 3 months ahead using the Ensemble model
- **Simulates** climate scenarios (Normal Year / Drought 2022 / Storm Marta 2025) with customisable parameters
- **Warns** about flood and drought thresholds in advance
The core scientific innovation is predicting **daily volume change (ΔV)** instead of volume directly, which avoids the "persistence trap" (NSE = 0.9994 for a model that just copies yesterday's value).
---
```
---
## Requirements
- **Python:** 3.9, 3.10, or 3.11 (recommended: 3.11)
- **OS:** Windows, macOS, or Linux
- **RAM:** At least 4 GB (8 GB recommended for DL training)
- **Disk:** At least 500 MB free
---
## Installation
### Step 1 — Clone or download the project
```bash
# If you have git:
git clone
github.com
cd idriss-dam-ai
# Or just download the ZIP and extract it, then open a terminal in the folder
```
### Step 2 — Create a virtual environment (recommended)
```bash
# Windows
python -m venv venv311
venv311\Scripts\activate
# macOS / Linux
python3 -m venv venv311
source venv311/bin/activate
```
### Step 3 — Install dependencies
```bash
pip install -r requirements.txt
```
**Or install manually:**
```b …