Predicting Nitrous Oxide Emission From China's Waterbodies With Multiple Deep Learning Algorithms
Bibliographic record
Abstract
Abstract Many studies have been conducted on the prediction of nitrous oxide (N2O) emissions from soils. Comparably, prediction of N2O water–air emissions is much more limited, especially at the national level. Here, we collected published N2O emission data across China's watersheds and analyzed spatiotemporal patterns during dry and wet seasons. We predicted N2O emission fluxes from these waterbodies for 2026–2028 using a traditional gray prediction model (GM) coupled with several deep learning models: Long Short‐Term Memory (LSTM), Gated Recurrent Unit (GRU), and Bidirectional Long Short‐Term Memory (BiLSTM). The study showed large regional variation in emissions from subtropical to boreal watersheds. Average emission rates varied from 13.95 (±27.15) μg m−2 h−1 in the Yellow River Basin to 68.71 (±102.62) μg m−2 h−1 in Southwest China. N2O emissions were clearly higher in the dry season than the wet season in all regions except the Yellow River Basin, indicating strong influence from wetland vegetation. Regarding model performance, higher accuracy was achieved by GRU and BiLSTM, which successfully predicted fluctuating increases of N2O emission fluxes in most regions from 2026 to 2028, reflecting seasonal changes. While LSTM performed less accurately, GRU and BiLSTM, evolved from LSTM, may be more appropriate for complex situations. These findings provide insights into national spatiotemporal patterns of N2O emissions and can guide regional and national mitigation strategies as well as future research.
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) | 0.001 | 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 | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".