Franz Pablo Antezana Lopez

Biomass burning is a major source of atmospheric trace gases and aerosols, and Amazonian fires are among its most intense sources globally, with documented impacts on the carbon cycle and regional climate. Long-range transport of Amazonian smoke toward Andean and coastal cities has been reported in individual case studies, but its continental-scale atmospheric footprint, and how it translates into population exposure and health outcomes across South America, remains poorly quantified. Here, we address this gap by combining Lagrangian plume tracking, regional chemical transport modeling (WRF-Chem), satellite fire data, and health-impact functions to characterize how Amazonian burning perturbs atmospheric composition across the continent and how that perturbation drives population exposure in major South American cities. We show that Amazonian burning generates a recurrent, continental-scale smoke season during the austral dry season (June–November), with transport corridors carrying fire-derived PM2.5 to cities along the Andes, the Pacific coast, southeastern Brazil, and the southern cone. This atmospheric perturbation is substantial: WRF-Chem simulations indicate 50–100 μg/m3 of added PM2.5 across the basin during peak months, translating into an estimated 33,000 (CI:19,700–48,900) excess premature deaths annually across South America. Fire trends reveal strong geographic contrasts linked to land-use dynamics and governance, and countries that have already curbed Amazonian fires show that the tools to reduce this burden exist wherever political will meets social awareness. As climate change reshapes fire regimes and these transport corridors, whether governance and mitigation efforts can keep pace with the resulting burden remains an urgent open question.

Carbon dioxide emissions, as geospatial information, are necessary to analyze seasonal and regional variability, as well as the changing distribution of anthropogenic activity. However, the availability of continuous data with high spatial and temporal resolution is limited, both sectorial and global. Therefore, in this study, we present the Hierarchical Bayesian Physics-Guided Carbon Dioxide (HBPG-CO2) emission dataset, a global dataset of emissions from multiple sources for energy, industry, buildings, land transport, agriculture, waste, and fuel production. This dataset is based on multi-information harmonization and downscaling using geospatial information from multiple sources (nighttime lighting, roads, land use, population, settlements, meteorology, and point source data support temporal reconstruction and spatial refinement), various emissions inventories such as annual and monthly data from the Emissions Database for Global Atmospheric Research (EDGAR), as well as the Open source Data Inventory for Anthropogenic Carbon dioxide (ODIAC), Community Emissions Data System (CEDS), and daily estimates by country and sector. To integrate all the data, a hierarchical Bayesian component is applied to reconstruct monthly variability outside the directly observed period, while a physics-based component restricts the specific spatial allocation for each sector and preserves emissions data, while also allowing for area expansion based on decision trees. Furthermore, the integration of fossil fuel-related covariates that are underrepresented or absent in the original EDGAR fields helps reconstruct this dataset spatially and temporally. The resulting dataset contains 672 monthly layers per sector and global layers corresponding to the date range from 1970-01 to 2025-12. Comparisons with CEDS, ODIAC, EDGAR, and other studies show strong temporal and spatial consistency, while also preserving additional small-scale structure. Therefore, HBPG-CO2 provides a long-term, high-resolution, sector-specific emissions record for atmospheric inversion, Earth system modeling, carbon cycle analysis, and regional emissions assessment. The complete HBPG-CO₂ dataset is openly accessible through Zenodo at https://doi.org/10.5281/zenodo.21507026 (Antezana Lopez, 2026).

Geological hazards in mountainous basins commonly arise from overlapping landslide, subsidence, and uplift processes, yet susceptibility mapping remains limited by incomplete inventories and poorly quantified predictive uncertainty. This study proposes a Bayesian deep-learning framework for probabilistic multi-hazard susceptibility mapping by integrating Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) deformation measurements with geological, geomorphological, edaphic, climatic, land-use, and multispectral covariates. The training inventory is strengthened through physically guided label refinement based on slope and deformation thresholds derived from SBAS-InSAR, and its reliability is independently evaluated prior to model training. Bayesian convolutional and multilayer perceptron models with Monte Carlo dropout are then used to estimate class probabilities together with predictive uncertainty. Independent validation of the integrated inventory yields an overall reliability of 79.48%. Under the original validation setting, the Bayesian CNN achieves an accuracy of 0.94 and an AUCROC of 0.99, while spatial block cross-validation confirms a more conservative but methodologically stronger estimate of generalization under clustered deformation samples. The resulting susceptibility maps show spatial agreement of 76% and 72% with independent landslide and subsidence inventories, respectively. High-susceptibility zones indicate that subsidence affects 11.6% of the basin, landslides 2.2%, and uplift 1.3%, all with strong spatial clustering (Moran’s I = 0.62–0.90). Compared with deterministic baselines, the Bayesian framework improves probability calibration and enables spatial separation of observation-driven and model-driven uncertainty. A decision-grade reliability mask derived from the validation coverage–risk frontier further allows unreliable predictions to be excluded explicitly. These results demonstrate that uncertainty-aware SBAS-InSAR susceptibility mapping can provide more reliable and operationally interpretable products for regional hazard assessment, planning, and early warning.

This study presents the development of a cost-effective Raspberry Pi-based electric piezocone system for Cone Penetration Testing with pore pressure measurement (CPTu). By utilizing a Raspberry Pi 4B as the data acquisition system (DAS), the proposed system offers a viable alternative to high-cost commercial geotechnical equipment, particularly in developing regions such as Bolivia. The system integrates high-precision sensors to measure tip resistance (qc), sleeve friction (fs), and pore-water pressure (u2), ensuring accurate real-time soil characterization. Field validation demonstrated a strong correlation between the Raspberry Pi-based system and a commercial CPTu, with Pearson’s r coefficients of 0.69 for sleeve friction and 0.59 for tip resistance. The root mean square error (RMSE) for tip resistance was 2.236 MPa. At the same time, for sleeve friction, it was 46.143 kPa, indicating that while the system provides reliable data, further calibration may improve accuracy. The soil classification results identified predominant layers of stiff sand and sand with silt, aligning with conventional CPTu interpretations. The affordability and adaptability of this system make it a practical solution for geotechnical investigations in resource-constrained environments, offering a functional alternative at a significantly lower cost than commercial CPTu systems. The use of open-source technology also enables real-time data monitoring, customization, and potential integration with machine learning for automated soil classification. Future research will focus on refining sensor calibration, enhancing data analytics, and expanding Internet of Things (IoT) capabilities to improve remote monitoring and streamline geotechnical testing applications.

Desertification threatens the sustainability of dryland ecosystems, yet many existing monitoring frameworks rely on static maps, coarse spatial resolution, or lack temporal forecasting capacity. To address these limitations, this study introduces PyGEE-ST-MEDALUS, a novel spatiotemporal framework combining the full MEDALUS desertification model with deep learning (CNN, LSTM, DeepMLP) and machine learning (RF, XGBoost, SVM) techniques on the Google Earth Engine (GEE) platform. Applied across Tebessa Province, Algeria (2001–2028), the framework integrates MODIS and Sentinel-1/-2 data to compute four core indices—climatic, soil, vegetation, and land management quality—and create the Desertification Sensitivity Index (DSI). Unlike prior studies that focus on static or spatial-only MEDALUS implementations, PyGEE-ST-MEDALUS introduces scalable, time-series forecasting, yielding superior predictive performance (R² ≈ 0.96; RMSE < 0.03). Over 71% of the region was classified as having high to very high sensitivity, driven by declining vegetation and thermal stress. Comparative analysis confirms that this study advances the state-of-the-art by integrating interpretable AI, near-real-time satellite analytics, and full MEDALUS indicators into one cloud-based pipeline. These contributions make PyGEE-ST-MEDALUS a transferable, efficient decision-support tool for identifying degradation hotspots, supporting early warning systems, and enabling evidence-based land management in dryland regions.

The harmonized multi-sensor satellite data assists users by providing seamless analysis-ready data with enhanced temporal resolution. The Harmonized Landsat Sentinel (HLS) product has gained popularity due to the seamless integration of Landsat OLI and Sentinel-2 MSI, achieving a temporal resolution of 2.8 to 3.5 days. However, applications that require monitoring intervals of less than three days or cloudy data can limit the usage of HLS data. Gaofen-1 (GF-1) Wide Field of View (WFV) data provides the capacity further to enhance the data availability by harmonization with HLS. In this study, GF-1/WFV data is harmonized with HLS by employing deep learning-based conditional Generative Adversarial Networks (cGANs). The harmonized WFV data with HLS provides an average temporal resolution of 1.5 days (ranging from 1.2 to 1.7 days), whereas the temporal resolution of HLS varies from 2.8 to 3.5 days. This enhanced temporal resolution will benefit applications that require frequent monitoring. Various processes are employed in HLS to achieve seamless products from the Operational Land Imager (OLI) and Multispectral Imager (MSI). This study applies 6S atmospheric correction to obtain GF-1/WFV surface reflectance data, employs MFC cloud masking, resamples the data to 30 m, and performs geographical correction using AROP relative to HLS data, to align preprocessing with HLS workflows. Harmonization is achieved without using BRDF normalization and bandpass adjustment like in the HLS workflows; instead, cGAN learns cross-sensor reflectance mapping by utilizing a U-Net generator and a patchGAN discriminator. The harmonized GF-1/WFV data were compared to the reference HLS data using various quality indices, including SSIM, MBE, and RMSD, across 126 cloud-free validation tiles covering various land covers and seasons. Band-wise scatter plots, histograms, and visual image color quality were compared. All these indices, including the Sobel filter, histograms, and visual comparisons, indicated that the proposed method has effectively reduced the spectral discrepancies between the GF-1/WFV and HLS data.

Dissolved Oxygen (DO) is an important water quality indicator, reflecting aquatic ecological health and influencing biological and biogeochemical cycles. Remote sensing of DO is exigent yet intricate due to its weak correlation with water optical properties. This study addresses this gap by integrating deep learning (DL) techniques with Chlorophyll-a (Chl-a), temperature, and temporal features. We employed a novel indirect approach to first estimate Chl-a and temperature using in-situ time series water quality data from 94 monitoring stations across the Hong Kong coast, covering five years (2019–2023), Sentinel-2 remote sensing data and normalized cyclic month features using machine learning algorithm eXtreme Gradient Boosting (XGB) and then utilized these predicted Chl-a and temperature values, along with normalized cyclic month features, to estimate DO leveraging DL technique two-dimensional convolutional neural network (2D CNN). XGB model achieved its accuracy in estimation of Chl-a (r = 0.78, RMSE = 3.16 μg/L, MAE = 2.31 μg/L) and temperature (r = 0.96, RMSE = 1.14 °C, MAE = 0.89 °C). 2D CNN yielded a promising DO estimation accuracy (r = 0.78, RMSE = 0.67 mg/L, MAE = 0.52 mg/L). This indirect DO estimation approach achieved 50% greater accuracy than direct methods and also showed 10% improvement in r, 8%–17% reduction in RMSE-MAE values over models trained using Chl-a and temperature only, highlighting the unique potential of XGB-2D CNN approach, incorporating cyclic month features. Inclusion of cyclic month features alongside Chl-a and temperature enabled the model to capture both seasonal variations and long-term trends, significantly enhancing the predictive performance of DO estimations. Consequently, monthly/seasonal mean products of Chl-a, temperature, and DO were generated for spatio-temporal analysis for practical use.

Groundwater level monitoring is crucial for assessing hydrological responses to climate change and human activities, which pose significant threats to the sustainability of semi-arid aquifers and the cultural heritage they sustain. This study presents an integrated remote sensing and transformer-based deep learning framework that combines diverse geospatial datasets to predict spatiotemporal variations across the plain near the Persepolis and Naqsh-e Rustam archaeological complexes—UNESCO World Heritage Sites situated at the plain’s edge. We assemble 432 synthetic aperture radar (SAR) scenes (2015–2022) and derive vertical ground motion rates greater than −180 mm yr⁻¹, which are co-localized with multisource geoinformation, including hydrometeorological indices, biophysical parameters, and terrain attributes, to train transformer models with traditional deep learning methods. A sparse probabilistic transformer (ConvTransformer) trained on 95 gridded variables achieves an out-of-sample R² = 0.83 and RMSE = 6.15 m, outperforming bidirectional deep learning models by >40%. Scenario analysis indicates that, in the absence of intervention, subsidence may exceed 200 mm per year within a decade, threatening irreplaceable Achaemenid stone reliefs. Our results indicate that attention-based networks, when coupled to synergistic geodetic constraints, enable early-warning quantification of groundwater stress over heritage sites and provide a scalable template for sustainable aquifer governance worldwide.