Research library
Evidence worth
understanding.
Read the question, method, findings and limits behind selected water-engineering research.
A curated foundational collection, not an exhaustive or live research feed. Publication dates and original sources are shown in each summary.
Demand forecasting
Improving short-term water demand forecasting using evolutionary algorithms
- Journal
- Scientific Reports 12, 13522
- Geography
- Wrocław, Poland
- Method
- Evolutionary strategies; regression; comparative forecasting
- Keywords
- demand, seasonality, forecasting, machine learning
How weekly seasonality informed a forecasting comparison in one Wrocław supply district.
Planning relevanceTest weekly seasonality before increasing forecast complexity.
Research summary · 2 min read
Read research summary
HydrologyRainfall–runoff modelling using Long Short-Term Memory networks
- Journal
- Hydrology and Earth System Sciences 22, 6005–6022
- Geography
- United States catchments (CAMELS)
- Method
- LSTM; hydrological benchmarking; regional transfer
- Keywords
- rainfall, runoff, hydrology, deep learning
A foundational evaluation of sequence learning across 241 catchments.
Planning relevanceEvaluate inflow models across catchments and flow regimes.
Research summary · 2 min read
Read research summary
UncertaintyUncertainty estimation with deep learning for rainfall–runoff modeling
- Journal
- Hydrology and Earth System Sciences 26, 1673–1693
- Geography
- Hydrological benchmark study
- Method
- Mixture density networks; Monte Carlo dropout
- Keywords
- uncertainty, deep learning, rainfall, runoff
Why a useful hydrological forecast needs more than one predicted value.
Planning relevanceCarry predictive uncertainty into water-security assessment.
Research summary · 2 min read
Read research summary
No articles in this selection. Choose another topic.