What question did this study set out to answer?

This study aims to develop a machine learning-based remote sensing method for efficient hydrogen exploration.

February 28, 2026Scientific Reports0 citationsOpen Access

Integrated pixel-wise remote sensing and explainable machine learning for natural hydrogen exploration in southeastern part of Pricaspian Basin, Western Kazakhstan

DWDennis Delali Kwesi Wayo LGLeonardo Goliatt RHRandy Hazlett

Key Points

This study aims to develop a machine learning-based remote sensing method for efficient hydrogen exploration.
Utilized Sentinel-2 imagery with 22 input features including spectral bands and indices.
Trained four classifiers on a dataset of over 120 million labeled pixels.
Applied explainable AI techniques to interpret the models' predictions.
XGB and LGBM classifiers achieved high recall rates of 91.8% and 93.1% respectively.
Low precision scores indicate challenges in rare-event detection.
Final predictions revealed spatial correlations with geological features, aiding in target identification.

Abstract

Natural hydrogen (H2) emerges as a clean energy resource generated by different geological processes in multiple geological contexts. Current hydrogen exploration activities rely mainly on surface geochemical surveys focused on diagnostic morphological expressions. Analogous to the early stages of hydrocarbon exploration, these first-pass indicators are used to delineate prospective corridors and rank targets, thereby de-risking and guiding subsequent subsurface investigations. However, these surface expressions remain elusive due to sparse sampling and the absence of robust detection workflows. This study presents a machine learning-based remote sensing technique for pixel-wise hydrogen prospectivity mapping applied on the Atyrau region in the southeastern part of the petroliferous Pricaspian Basin, western Kazakhstan. We utilize Sentinel-2 Level-2 A imagery and extract 13 spectral bands (B1–B12, B8A), 5 spectral indices (e. g. , NDVI, NDWI), and 4 texture features, forming a 22-dimensional input feature space. Four classifiers, Random Forest (RF, n=200), eXtreme Gradient Boosting (XGB, n=100, max depth = 5), Stochastic Gradient Descent (SGD, loss = log), and LightGBM (LGBM, learning rate = 0. 1), were trained on 120, 560, 400 labeled pixels with 4, 621, 344 positive labels derived from high-confidence expert polygons. Performance metrics revealed strong recall for XGB (91. 8%) and LGBM (93. 1%), albeit with lower precision (6. 8% and 6. 4% respectively), reflecting class imbalance and rare-event detection challenges. The ROC AUC ranged from 0. 50 (SGD) to 0. 81 (XGB), with Precision-Recall AUC peaking at 0. 17 for RF. Explainable AI techniques based on SHAP (SHapley Additive Explanations) were applied to quantify pixel-wise feature contributions for each classifier. SHAP attributions, overlaid on geologic cross-sections, revealed spatial correlations with known faults and surface anomalies. Final predictions, rasterized into labeled GeoTIFFs at 10 m resolution, indicate locations of anomalies. These promising screening-type exploration results allow for narrowing down areas for direct surface measurements and focusing on understanding the hydrogen system and play concepts. This demonstrates that workflow provides a scalable, interpretable, and cost-effective methodology for natural hydrogen exploration and can be adapted to other data-sparse basins worldwide.

Ask AI

Helpful

Bookmark

View Full Paper