TrendeX expected-greenness model (v1)

Predicts the summer greenness (NDVI) anomaly of every 1 km pasture cell in Naryn oblast, Kyrgyzstan (May-September, 2001-2025) from weather and terrain alone. The gap between observed and expected NDVI is change not explained by precipitation, temperature, snow and soil moisture. It is not a cause and says nothing about forage quality. Built for NASA Space Apps 2026 ("Be An Earth System Trend Detective!").

Inputs

  • Weather anomalies vs each cell's 2001-2025 mean for the same month: GPM IMERG precipitation (month, 3-month, Oct-Apr), MODIS LST day/night (month, previous month), MODIS snow (Mar-May, month), GLDAS soil moisture (month) and April snow water.
  • Terrain from NASADEM (elevation, spread, slope, steep share, aspect, TPI) and land cover (MCD12Q1 2020).
  • The cell's own NDVI climatology for that month. Not used on purpose: year, coordinates, past NDVI.

How it was tested (protocol locked in git before the first fit: model_v1.yaml, commit 92ed159)

  • Tuning only on 2001-2015 -> 2016-2019. The 2020-2025 years were used once, for the final test.
  • Spatial test: 5-fold GroupKFold over ~30 x 30 km super-blocks (all years; easier than the temporal test because the same years' weather appears in training).
  • Baselines: climatology (anomaly = 0) and ridge regression on the same features.
  • Pre-registered gate: ship XGBoost only if the 95% CI lower bound of its skill over ridge is > 0 on both tests. Gate passed: True. Shipped: xgb.
Test RMSE xgb RMSE ridge RMSE climatology anomaly corr xgb anomaly corr ridge tercile bal. acc. xgb
Temporal (2020-2025) 0.0554 0.0588 0.0616 0.424 0.288 0.455
Spatial (unseen areas) 0.0523 0.0578 0.0619 0.540 0.358 0.524
  • Skill vs ridge, temporal: 0.113 (95% CI 0.089 to 0.133, 6 units). Five seeds: 0.110 +/- 0.003.
  • Skill vs ridge, spatial: 0.180 (95% CI 0.169 to 0.192, 76 units).
  • Skill vs climatology, temporal: 0.191 (95% CI 0.160 to 0.215, 6 units).
  • What each NASA dataset adds (skill vs climatology, temporal test): precip: 0.055 -> +lst: 0.167 -> +snow: 0.181 -> +gldas (full): 0.188.
  • Most used inputs: lst_day_m, lst_day_prev, precip_3m, lst_night_m, soil_m, month.

Limits (read before using)

  • The model explains about a fifth of the year-to-year NDVI anomaly on unseen years; most variation is not weather-explained.
  • P10-P90 band: on 2020-2025 it covered 74% instead of 80%, so treat it as too narrow.
  • Weather comes from coarse grids (IMERG 0.1 deg, GLDAS 0.25 deg) interpolated to 1 km.
  • NDVI is greenness, not forage: shrub encroachment can look like improvement.
  • Land cover is a fixed 2020 map; MODIS Terra drifted in recent years (see Aqua-Terra check in the dataset products).
  • What-if runs: drier and hotter-than-normal conditions lower expected July NDVI, but wetter-than-normal precipitation does not raise it (slightly lowers it on average). Treat what-if outputs as model sensitivities, not causal effects.
  • No field validation. Relative to Naryn pastures only.

Use

from predict import load
m = load(".")                                  # needs only numpy, pandas, xgboost (CPU)
out = m.predict(features_df)                   # columns as in feature_schema.json
scen = m.what_if(cells, cell_ids, month=7, precip_pct=-30)   # cells = naryn-cube cells.parquet

pytest test_golden.py reproduces the 100 golden rows.

Data and tools

MOD13A3.061, MYD13A3.061, MOD11A2.061, MOD10A2.061, MCD12Q1.061, NASADEM_HGT.001 (LP DAAC / NSIDC via earthaccess), GPM_3IMERGM.07 and GLDAS_NOAH025_M.2.1 (GES DISC). XGBoost, Optuna, scikit-learn, pymannkendall. AI use: implementation was assisted by Claude (Anthropic); design decisions and the product idea are the team's.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Dataset used to train TrendeX90/expected-greenness