Skip to content
6-Week Hands-On Workshop
Hosted by Teesside University • Supported by The Royal Society

AI in Water Quality:
Assessment • Prediction • Management

From No-Code to AI-Assisted Research. Learn practical AI techniques to evaluate, forecast, and manage water quality for a cleaner, healthier, and sustainable future.

Duration

6 Live Sessions

Prerequisite

No-Code to Low-Code

Target Audience

Scientists & Researchers

Final Project

Real-World Capstone

General Training Outline

A comprehensive framework designed to take researchers from raw data collection to automated AI decision-making systems.

1. ASSESS

Evaluate water quality metrics from real-world environmental data using AI.

2. PREDICT

Forecast contaminants, trends, and water quality indices (WQI).

3. MANAGE

Support strategic decision-making and optimize water resource management.

4. AUTOMATE

Build smart workflows and real-time early warning monitoring systems.

5. IMPACT

Deliver data-driven solutions for cleaner water and sustainable futures.

Course Materials Access

Weekly Curriculum & Resources

Introduction to water quality parameters, environmental data structures, and navigating no-code AI tools for rapid exploratory assessment.

Classification, Regression, and Clustering using LazyPredict and Scikit-Learn to evaluate water potability and predict water quality metrics from real-world datasets.

Building neural network architectures, tracking loss across epochs, and comparing neural network detection accuracy against Random Forest models while navigating decision explainability trade-offs.

Transitioning from engineer to scientist using Generative AI. Mastering the RCTAF prompting framework for Claude and leveraging NotebookLM for source-grounded literature synthesis and gap identification[cite: 50, 51, 62].

Collaborating Institutions & Partners

Data Crunch
AI Hub
Teesside University
Université de Kinshasa
UNISA