Increased Streamflow Intermittence in Europe due to Climate Change Projected by Combining Global Hydrological Modeling and Machine Learning
Bibliographic record
Abstract
Freshwater biodiversity and ecosystem services are under stress as climate change alters streamflow intermittence. Some historically perennial rivers are now drying in most years, while non-perennial streams that once flowed into summer are reduced to disconnected pools by spring. We present the first continental-scale quantification of future climate change impacts on streamflow intermittence, achieved for Europe at a high spatial resolution that captures headwater streams. A hybrid modeling approach combined physics-based and data-based modeling, whereby a random forest model, trained on historical data, uses predictor values representing the impact of the changing climate on high-resolution (500 m) streamflow. These predictors were derived from the output of the low-resolution (50 km) global hydrological model WaterGAP, which was driven by bias-adjusted outputs of five global climate models. The generated monthly time series of intermittence status for over 1.5 million reaches were used to calculate five ecologically relevant indicators of streamflow intermittence change. In Europe, the number of non-perennial reach-months is projected to increase in the future, for both high (SSP5-RCP8.5) and low (SSP1-RCP2.6) greenhouse gas emissions scenarios, in almost all climate zones and in particular in August and September. Under SSP5-RCP8.5, 4.8% of all reach-months will experience no-flow conditions in the 2080s, up from 3.5% in 1985-2014, while only a small increase to 3.8% is projected under SSP1-RCP2.6. With high emissions, 2.8% of the European reaches are projected to shift from being perennial to being non-perennial by the 2080s, even in areas with increased annual precipitation, and 0.7% from non-perennial to perennial.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".