COVID-19 monitoring data from wastewater.

A Unified Python Interface for Water Resource Data Acquisition

Supplementary files for "Integrated Design and Optimization of Water-Energy Nexus: Combining Wastewater Treatment and Energy System"

A knowledge graph of the wastewater treatment microbiome and its biological context

A Julia Modelingtoolkit.jl Implementation of Anaerobic Digestion Model No.1 (ADM1)

Comparison of clustering methods for determining the operational states of a wastewater treatment plant (BSc project in Statistics) 🔧 🚰 🔄 ♻️ 💦

AI-driven predictive modeling for wastewater treatment optimization. Utilizing the UCI dataset to develop virtual soft-sensors for BOD/COD monitoring and operational sustainability.

Data and code for LaMartina et al., 2021

Training stiff NODE in data-driven wastewater process modelling

Reproducible deep-learning image-classification pipeline for industrial soft sensing. Originally built for sludge-cake quality monitoring at DC Water Blue Plains AWWTP. Six architectures (FastViT, EfficientNet, MobileNet, EfficientFormerV2, DeepTEN-ResNet, sparse-AE CNN) compared with multi-seed statistics on Modal cloud GPUs.

Official AQUALIS resources for stormwater, wastewater, and pond management; environmental compliance, maintenance, and best practices.

N2O Digital Twin for wastewater treatment — predicts N2O emissions up to 60 minutes ahead (6-step multi-horizon) using 10-minute interval time-series data. Built with XGBoost + LSTM ensemble model, FastAPI backend, and a static frontend dashboard for operational decision-making (e.g., DO control scenarios).

Documentation for the PooPyLab Project

Multi-agent RL for wastewater treatment plant control (BSM2/Simulink) — MSc Thesis

Python framework for matrix-aware kinetic and process-level evaluation of advanced oxidation processes in wastewater treatment.

Statistical Optimization of Multi-Factor Adsorption Processes Using Factorial ANOVA: A JASP-Based Methodology Demonstration | Synthetic dataset (n=2,304), Python data generation, JASP analysis workflow | Open Science

A R-Shiny web application to access, visualize and analyze cw research data.

Processed 43,000+ records with 42 variables, using lubridate for time series manipulation. Visualized key variables like pH levels and membrane permeate flow, identifying a critical fault event. Developed regression models (linear, stepwise) and used Lasso (cv.glmnet) to improve predictive accuracy for pH levels and fault detection.

一款污水处理脱氮除磷相关计算软件。基于德国DWA、ATV协会的技术规范

An end-to-end MLOps pipeline that predicts wastewater aeration needs using BSM1 simulation data. Features time-series forecasting, model serving, and data drift monitoring.