Reliability of Artificial Intelligence-based Models Compared to Numerical Model for Predicting Groundwater Level under Changing Climate
Bibliographic record
Abstract
Groundwater modeling is a crucial tool for simulating groundwater level behavior under future climate change scenarios, and for studying the effects of water management strategies on sustainability of groundwater resources. In this study, two types of models, namely, a physical-based numerical model called MODFLOW, and a data-driven model called Genetic Algorithm-based Multilayer Perceptron (MLP-GA), were evaluated for the reliable predictions of groundwater levels in the semi-arid region of the Karnal district, Haryana. Seven hybrid MLP-GA models were developed with different combinations of input variables such as rainfall, crop evapotranspiration, deep percolation, and irrigation water requirement. The numerical model and hybrid MLP-GA models were calibrated and validated using groundwater-level data from the pre-monsoon period. Among the hybrid models, the model M-1 with four input variables (crop evapotranspiration, rainfall, deep percolation, and applied irrigation water) and 4-29-1 (four input nodes, 29 neurons in the hidden layer, and one output node) model architecture performed the best, but the numerical model showed superiority over the MLP-GA models. The numerical model and M-1 model were used to predict future groundwater levels under projected climate change scenario. According to the numerical model, under the RCP4.5 scenario, groundwater levels in the study area were projected to decline by 7.7 meters by the year 2039 compared to the reference year of 2015. The M-1 model predicted decline of 5.0 meter by the year 2039. The study concluded that all input variables are essential for accurately simulating groundwater levels using MLP-GA models, and that the numerical model is more reliable for assessing the impact of climate change on groundwater behavior during future periods.
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 | 0.003 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 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 | 0.001 |
| 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".