physics.ao-phOct 20, 2026
SaveTerraNostra-Bench: Benchmarking Spatial Downscaling and Temporal Rollout for Global 1-km Land-Use Reconstruction
Organizations: Earth Science Department, Barcelona Supercomputing Center (BSC), Barcelona, Spain · Foundation Euro-Mediterranean Center on Climate Change, Bologna, Italy · AI Institute, Barcelona Supercomputing Center (BSC), Barcelona, Spain
Abstract
Uncertainty in the terrestrial carbon cycle remains a major constraint in climate projections, partly due to imperfect land surface representations in Earth system models. We propose a data-driven framework for high-resolution land-use reconstruction, treated as a semantic-segmentation task, that combines coarse-resolution scenario data and climate classification with static geophysical features to produce annual land-use maps at 1 km resolution. We introduce TerraNostra-Bench, a change-aware evaluation protocol that separates spatial downscaling from autoregressive temporal rollout and scores models on the rare land-use-change pixels rather than the dominant static background. Using it, we compare convolutional (U-Net) and transformer (Swin) backbones in autoregressive and non-autoregressive schemes against persistence, linear, and shallow convolutional baselines. The autoregressive prior is the most informative input yet accumulates error over long rollouts: autoregressive models lose 5.7-7.2 accuracy points over 13 years, against 2.2-2.8 for non-autoregressive models. This trade-off is governed by the autoregressive choice rather than the backbone. It can be tuned by an inference-time prior-trust threshold that requires no retraining and by the training-time weighting of reconstruction and change objectives; the two levers trace complementary frontiers, with calibration recovering up to 10 accuracy points while keeping change sensitivity above the persistence floor. Extrapolating beyond the training window, backward to 1955-1959 and forward to 2015-2019 under scenario forcing, the models retain most of their in-window skill and show the same trade-off, indicating it is intrinsic to the design. This work provides the methodological foundation and evaluation surface for a forthcoming temporally continuous land-use product.
Figures & tables
Figure 1: Annual global carbon emissions and their partitioning from 1850 to present. The data highlights the significant and persistent contribution of net land-use change emissions (ELUC, orange) to the atmospheric carbon burden, alongside fossil emissions. Source: Global Carbon Budget 2025 ( Friedlingstein et al., 2025 )
| HILDA+ (Original) | TerraNostra (Target) | LUH2 (Predictors) | |||
|---|---|---|---|---|---|
| Code | Class Name | Code | Class Name | Abbr. | Full Class Name |
| 11 | Urban | 1 | Urban | primf | Primary Forest |
| 22 | Cropland | 2 | Cropland | primn | Primary Non-Forest |
| 33 | Pasture | 3 | Pasture | secdf | Secondary Forest |
| 40 | Forest (Unknown/Other) | 4 | Forest | secdn | Secondary Non-Forest |
| 41 | Forest (Evergreen, needle) | 5 | Grass/shrubland | pastr | Managed Pasture |
Table 1: Overview of Land Use/Land Cover taxonomies and predictor variables. The table displays the original HILDA+ classes, the consolidated TerraNostra target classes, and the LUH2 predictor variable definitions.
Figure 2: Temporal Data Scope. An overview of the dynamic and static predictors along with the target variable over the historical and future timelines.
Figure 3: Architecture & Autoregressive Prior. A schematic of the neural network architecture and the autoregressive training strategy.
Figure 4: Validation-loss convergence for the non-autoregressive runs and the learnable baselines. The linear model (top panel) at a much higher validation loss ( ) than the deep models ( – , bottom panel), quantifying the value of spatial context.
| Overall | Land-use change | |||
|---|---|---|---|---|
| Model | Acc. | mIoU | Acc. | mIoU |
| Rolling persistence | 0.9947 | 0.9890 | 0.0000 | 0.0000 |
| Frozen persistence | 0.9704 | 0.9419 | 0.1630 | 0.0883 |
| Linear | 0.8058 | 0.3988 | 0.3510 | 0.1458 |
| Simple CNN | 0.8193 | 0.4879 | 0.3603 | 0.1466 |
| AR U-Net | 0.8072 | 0.4218 | 0.3931 | 0.1661 |
Table 2: Overall versus land-use-change performance (5-seed means, 2001–2014 average). Overall accuracy is dominated by the pixels that stay in the same class between consecutive years, so persistence baselines are unbeatable on this axis; the land-use-change regime—the scientifically meaningful signal—measures accuracy only on the pixels that actually transitioned. The two regimes separate the models cleanly: the non-autoregressive variants lead on overall accuracy and mIoU, the autoregressive variants—trained with a change-weighted objective—lead on every change metric. The Linear and Simple CNN baselines obtain generally worse results across the metrics. mIoU is the macro-average of per-class IoU over the 7 land classes (Ocean excluded, as it is trivially separable at IoU 0.999 for every model). Accuracy columns are pixel-level micro averages. The two non-autoregressive overall-mIoU scores (0.5276, 0.5264) are within seed noise of each other.
| Model | Acc. | mIoU | Acc. | mIoU |
|---|---|---|---|---|
| Linear | -0.17% | +0.15% | -0.16% | -0.18% |
| Simple CNN | +0.02% | +0.20% | -0.13% | -0.24% |
| AR U-Net | -0.13% | -0.53 % | -0.19% | -0.38% |
| non-AR U-Net | -0.01% | -0.39% | -0.00% | -0.18% |
| AR Swin-ViT | +0.17% | +0.20% | +0.31 % | +0.08% |
Table 3: Padding effect on inference overall 14-Year rollout mean (3-seed means, 2001-2014 average).
Figure 5: Overall accuracy across the 14-year autoregressive rollout (5-seed mean, shaded 1 s.d.). All models decay, but autoregressive models show a much steeper decline than non-autoregressive models.
| Model | Year 0 | Year 13 | (Y0 Y13) |
|---|---|---|---|
| AR U-Net | |||
| AR Swin-ViT | |||
| non-AR U-Net | |||
| non-AR Swin-ViT | |||
| Simple CNN | |||
| Linear |
Table 4: Rollout endpoints (5-seed means s.d.). Overall accuracy at the first (2001) and last (2014) rollout year, and the change across the horizon. All models decline, including the Linear baseline, which carries no temporal state at all and therefore isolates the component of the decline attributable to the test years themselves rather than to error accumulation ( ). The autoregressive models lose a further – points beyond that floor, whereas the non-autoregressive models lose only – . Bold marks the best value among the four deep models.
Figure 6: Land-use-change accuracy across the rollout (5-seed mean, shaded 1 s.d.). All learned models far exceed the frozen-persistence floor (dotted); autoregressive variants lead on change detection.
| Removed input | Val. loss | % change | |
|---|---|---|---|
| Autoregressive HILDA+ prior | 0.6854 | ||
| Secondary non-forested ( secdn ) | 0.6322 | ||
| Primary non-forested ( primn ) | 0.6210 | ||
| C4 annual crops ( c4ann ) | 0.6181 | ||
| Köppen-Geiger class (dynamic) | 0.6151 | ||
| Secondary deciduous forest ( secdf ) | 0.6096 |
Table 5: Leave-one-out feature importance. Change in validation loss when each input (or group) is removed, relative to the full model (loss ); a positive means the feature is helpful. Köppen-Geiger and population are supplied as dynamic annual inputs. The autoregressive prior dominates.
| Removed input | Val. loss | % change | |
|---|---|---|---|
| Köppen-Geiger class (dynamic) | 0.8237 | ||
| Primary non-forested ( primn ) | 0.4291 | ||
| Secondary deciduous forest ( secdf ) | 0.4232 | ||
| Population (dynamic) | 0.4211 | ||
| Secondary non-forested ( secdn ) | 0.4131 | ||
| C4 annual crops ( c4ann ) | 0.4123 |
Table 6: Leave-one-out feature importance (non-autoregressive U-Net). Change in validation loss when each input (or group) is removed, relative to the full non-AR model (loss ); a positive means the feature is helpful. Without the autoregressive HILDA+ prior, the dynamic Köppen-Geiger class dominates, and removing whole feature groups is far more damaging than removing any single LUH2 channel. Absolute losses are not comparable to Table 5 , as the non-AR model is trained without the change-loss term.
| Class | AR U-Net | non-AR U-Net | AR Swin-ViT | non-AR Swin-ViT |
|---|---|---|---|---|
| Urban | 0.1864 | 0.2068 | 0.1994 | 0.2043 |
| Cropland | 0.5687 | 0.6410 | 0.6159 | 0.6381 |
| Pasture | 0.4785 | 0.5401 | 0.4676 | 0.5668 |
| Forest | 0.6760 | 0.7186 | 0.6512 | 0.7255 |
| Grass/shrubland | 0.2376 | 0.3605 | 0.3843 | 0.3568 |
| Other land | 0.7447 | 0.7430 | 0.5581 | 0.7763 |
Table 7: Per-class IoU (5-seed mean, 2001–2014 average) for the four learned variants. Non-autoregressive models lead on six of the seven classes; the AR Water collapse reflects rollout error accumulation on the one class for which the coarse forcing carries no direct evidence. The ocean class is excluded.
Figure 7: Per-class IoU across the four learned variants (5-seed mean, error bars 1 s.d., 2001–2014 aggregate). The autoregressive Water collapse and the difficulty of the rare Urban and Grass/Shrubland classes are visible, while the non-autoregressive variants lead on most classes.
Figure 8: Prior-trust calibration traces a stability–sensitivity frontier. Overall accuracy (stability) versus land-use-change macro-F1 (sensitivity) over the 14-year rollout, as the inference-time trust threshold is swept from 0.70 to 0.95 (circles: AR U-Net; diamonds: AR Swin-ViT; colour: threshold). Stars mark the vanilla autoregressive models (5-seed mean) and triangles the persistence baselines. Raising the threshold moves each model from the change-sensitive vanilla corner toward the stable persistence corner; the two architectures trace nearly the same curve.
Figure 9: Training-time loss balancing traces a stability–sensitivity frontier. Overall 14-year rollout accuracy (stability) versus land-use-change macro-F1 (sensitivity) as the loss weight is swept from to (circles: U-Net; diamonds: Swin-ViT; colour: ), five seeds per point. Increasing shifts weight onto the overall-reconstruction term, moving each model from the change-sensitive corner toward the stable-reconstruction corner; the canonical default (red edge) sits near the knee. Triangles mark the persistence baselines.
Figure 10: The two control levers trace overlapping but non-identical frontiers. Overall rollout accuracy (stability) versus land-use-change macro-F1 (sensitivity), overlaying the inference-time trust-threshold sweep (solid) and the training-time loss-balance sweep (dashed); circles denote U-Net and diamonds Swin-ViT. Stars mark the vanilla autoregressive models ( , ) and triangles the persistence baselines. The two levers coincide in the middle of the frontier but each reaches a region the other cannot: the trust threshold extends further toward the stable persistence corner, loss-balancing further toward the change-sensitive corner.
| Backward (1955–1959) | Forward (2015–2019) | |||
|---|---|---|---|---|
| Model | Overall Acc. | Change Acc. | Overall Acc. | Change Acc. |
| AR U-Net | 0.8246 | 0.3207 | 0.8140 | 0.4212 |
| non-AR U-Net | 0.8425 | 0.3559 | 0.8259 | 0.3923 |
| AR Swin-ViT | 0.8130 | 0.3010 | 0.8032 | 0.4452 |
| non-AR Swin-ViT | 0.8583 | 0.3312 | 0.8303 | 0.4131 |
| Simple CNN | 0.8280 | 0.2987 | 0.8082 | 0.4188 |
Table 8: Out-of-window extrapolation (5-seed means, 5-year rollout averages). Backward : 1955–1959, conditioned on 1960, historical forcing. Forward : 2015–2019, conditioned on 2014, SSP2-4.5 forcing (SSP3-7.0 and SSP4-6.0 agree to within ). Both windows are strictly outside the 1960–2000 training period. All learned models exceed the frozen-persistence change floor ( ).
Figure 11: Extrapolation in both temporal directions. Per-year overall accuracy for the backward (1955–1959) and forward (2015–2019, SSP2-4.5) rollouts, framing the in-window 2001–2014 period. Autoregressive models drift away from the conditioning anchor in both directions; non-autoregressive models remain flat.
Appendix figures & tables7 assets
Supplementary material from the paper’s appendix.
Appendix
Figure 12: Spatial five-fold split. Top: FPS patch centres coloured by their exclusive macro-cell fold assignment. Bottom: the five cross-validation rounds; each round trains on four folds (grey) and holds out one fold (colour) for testing. The canonical 70/15/15 split used in the main results is drawn from the same macro-cell machinery.
| Overall acc. | Macro F1 | Mean IoU | Change acc. | Change F1 | |
| Fold 0 | 0.793 | 0.688 | 0.562 | 0.429 | 0.281 |
| Fold 1 | 0.789 | 0.708 | 0.581 | 0.477 | 0.317 |
| Fold 2 | 0.764 | 0.712 | 0.582 | 0.452 | 0.311 |
| Fold 3 | 0.785 | 0.692 | 0.566 | 0.437 | 0.297 |
| Fold 4 | 0.757 | 0.688 | 0.558 | 0.434 | 0.285 |
| Fold mean std |
Table 9: Split sensitivity of the non-AR U-Net. Fourteen-year rollout means on the held-out fold of each cross-validation round, against the canonical-split reference (epoch-9 checkpoint; std over five evaluation seeds, i.e. pure sampling noise). Class-balanced metrics (macro F1, mean IoU) are insensitive to the split; overall accuracy varies with the regional class composition of the held-out area, as expected for spatial cross-validation.
| Overall acc. | Macro F1 | Mean IoU | Change acc. | Change F1 | |
| Fold 0 | 0.738 | 0.569 | 0.458 | 0.420 | 0.269 |
| Fold 1 | 0.777 | 0.667 | 0.545 | 0.457 | 0.267 |
| Fold 2 | 0.643 | 0.577 | 0.448 | 0.423 | 0.240 |
| Fold 3 | 0.746 | 0.601 | 0.484 | 0.413 | 0.254 |
| Fold 4 | 0.614 | 0.553 | 0.424 | 0.419 | 0.262 |
| Fold mean std |
Table 10: Split sensitivity of the AR U-Net. Fourteen-year rollout means on the held-out fold of each cross-validation round (best-validation checkpoints at epochs 2–3 under a fixed training budget), against the canonical-split model evaluated at matched maturity (epochs 2 and 3) and at its best-validation checkpoint (epoch 4; the setup reported in the main text). At matched budget the canonical scores are consistent with the fold distribution, but the fold spread is four times larger than for the non-AR model (Table 9 ) and orders by the land-use-change fraction of the held-out regions (folds 2 and 4, change pixels, score lowest) — the HILDA prior that feeds the autoregressive design is less informative where landscapes change.
Figure 13: High-change patch, northwest India ( N, E; 23% of pixels change class between 2000 and 2013). Rows: ground truth and the four models; columns: rollout years 0 (2000), 6 (2006) and 13 (2013). The number in each panel is its pixel accuracy against ground truth. All four models stay within a few points of each other throughout (68–72% at year 13), dip at year 6 and partly recover; all smooth the grass/shrubland mosaic into cropland.
Figure 14: High-change patch, Kansas City, USA ( N, W; 21% change). Layout as in Figure 13 . Accuracy falls for all models, slightly more for the autoregressive variants (AR U-Net , AR Swin-ViT ) than for the non-autoregressive ones ( for both). All models capture the urban core but smooth the surrounding pasture–cropland mosaic.
Figure 15: Moderate-change patch, US Great Plains ( N, W; 10% change). Layout as in Figure 13 . The non-autoregressive models remain nearly flat (U-Net , Swin-ViT ), as does the AR U-Net ( throughout), whereas the AR Swin-ViT declines from to . All models reproduce the large-scale pasture–cropland pattern but miss the river and its riparian vegetation.
Figure 16: Moderate-change patch, northern Cameroon ( N, E; 10% change). Layout as in Figure 13 . The clearest example of autoregressive drift: the AR U-Net falls from to and the AR Swin-ViT from to as both progressively overwrite the eastern pasture with cropland, whereas the non-autoregressive U-Net stays largely stable ( ) and the non-autoregressive Swin-ViT declines less ( ).
More in this topic
Land Cover Classification
Land cover classification assigns satellite, aerial, and LiDAR observations to classes such as forests, crops, water, and built areas.
See all 35 papers