Applying <scp>LSTM</scp> to Model Multi‐Depth Soil Moisture Under Various Land Covers, Climates and Soils
Bibliographic record
Abstract
ABSTRACT Accurate estimation of multi‐depth/profile soil moisture (SM) is required for sustainable water management in agriculture and hydrology. However, monitoring SM is costly and labour‐intensive, and only limited soil depths can be instrumented with soil moisture sensors. Therefore, various numerical simulation and data assimilation techniques have been used in multi‐depth soil moisture estimation. Machine learning (ML) has also gained popularity in SM estimation due to its ease of use and robustness, although proper handling of ML models also requires expertise and experience. However, the applicability of ML to estimate time series of multi‐depth SM under different land uses is mainly limited by the choice of ML models and the availability of SM data. In addition, the reliability of the trained model remains unknown when it is applied to different locations. Therefore, the objective of this study was to evaluate the widely used Long Short‐Term Memory (LSTM) model to estimate multi‐depth SM under different land covers, climates, and soils. A minimum of 10 years' daily meteorological and soil data at multiple depths were collected from six U.S. Climate Reference Network (USCRN) stations with different land covers and various climates and soils. These data were used to train the LSTM model and optimize its input parameters. Performance of the trained LSTM model was evaluated for multi‐depth SM estimation at two other “monitoring” stations with similar conditions. SM modeling at shallow depths (e.g., 5, 10 and 20 cm) was most accurate (< 10% mean absolute percent error, MAPE) with precipitation and antecedent time series of SM as inputs, while the best SM estimates at deeper depths (e.g., 50 and 100 cm) were attained with antecedent SM time series as the input. Generation of the trained LSTM model from one station to other stations emphasized on the similar soil and land cover conditions. It is hoped that this research would provide better understandings of multi‐depth SM modeling and offer new insights improving profile SM modeling accuracy for un‐instrumented sites.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| 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".