Machine learning in coupled wildfire-water supply risk assessment: Data science toolkit
Bibliographic record
Abstract
The frontier of wildfire-related risk assessment is moving into data science territory, and with good reason. Computational statistics, built on a foundation of high resolution remote sensing data, ground data, and theory, forms the basis of powerful risk assessment tools. The need for data based risk assessment has increased in past years, in view of longer wildfire seasons in the U.S., associated with more frequent droughts, more human ignitions and accumulating fuel loads. We present an application of machine learning (ML), which makes it possible to analyze complex data without a priori definition of interactions—this is a major advantage because these interactions are not known beforehand. Specifically, we build a stochastic gradient boosting machine (GBM) toolkit to assess the change in river flow after wildfire in the contiguous United States (CONUS) over a 5-year period. The GBM accounts for nonlinear relationships and interactions between wildland fire characteristics, watershed geometry, climate variability, topography and land cover. Building the GBM is a sequential process where a loss function is minimized at each fold, along a gradient defined by pseudo-residuals. This process allows the program to progressively learn more about how the variables in the large dataset interact to result in the response (i.e., river flow). Our results show that wildfires increase annual river flow in the CONUS when more than 20% of a gaged basin is burned. Data science tools like the GBM presented here, are essential in generating practical knowledge on how wildfire impacts on ecohydrology can ultimately affect hydrological services, socio-hydrosystems and water security in fire-affected regions.
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 | 0.006 | 0.018 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.005 | 0.003 |
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".