The long-term simulation of soil erosion and transport of contaminants and nutrients process in a river basin allows us to predict the impacts generated by the alterations of the environment and the scope of the potential contamination. The use of modeling tools such as SWAT (Soil and Water Assessment Tool) that integrates basin-level information on land use and management for hydrological simulation, requires specific data of soil and land use to define the Hydrological Response Units (HRU). These HRU are the basis of the simulation, grouping HRU according to hydrological response characteristics. The availability of quality data at the regional level is a key factor for obtaining robust models. One of the greatest shortcomings is found in obtaining hydropedological data bases associated with soil GIS shape.
4 November 2025 in Science of The Total Environment
The main objective of this study is the potential evaluation of obtaining bioplastics through biodegradable polyesters synthesized by bacteria, present in the anaerobic treatment of urban and industrial wastewater, which have a series of characteristics to consider as their processing as material bioplastic In Asturias, more than 70,000 tons of sludge are produced and, by applying circular economy criteria and technologies for the production of bioplastics from wastewater, a synergy could be obtained that would allow the reuse of sludge by valorization as raw material. to produce bioplastics. This valorization can be carried out mainly through the combination of two technologies, on the one hand, anaerobic fermentation to produce volatile fatty acids and on the other the generation of bacterial populations that produce Polyhydroxyalkanoates (PHA’s). The PHAs are obtained from the microorganisms present in the sludge generated in the wastewater treatment process.
Accurate global mapping of lunar iron oxide (FeO) abundance is essential for understanding the Moon’s geological evolution and for supporting future in situ resource utilization (ISRU). While hyperspectral data from the Moon Mineralogy Mapper (M3) provide a unique combination of high spectral dimensionality, hectometre-scale spatial resolution, and near-global coverage, existing FeO retrieval approaches struggle to fully exploit the high dimensionality, nonlinear spectral variability, and planetary-scale volume of the Global Mode dataset. To address these limitations, we present an integrated machine learning pipeline for estimating lunar FeO abundance from M3 hyperspectral observations. Unlike traditional methods based on raw reflectance or empirical spectral indices, the proposed framework combines Discrete Wavelet Transform (DWT), deep autoencoder-based feature compression, and ensemble regression to achieve robust and scalable FeO prediction. M3 spectra (83 bands, 475–3000 nm) are transformed using a Daubechies-4 (db4) DWT to extract 42 representative coefficients per pixel, capturing the dominant spectral information while filtering high-frequency noise. These features are further compressed into a six-dimensional latent space via a deep autoencoder and used as input to a Random Forest regressor, which outperforms kernel-based and linear Support Vector Regression (SVR) as well as Lasso regression in predictive accuracy and stability. The proposed model achieves an average prediction error of 1.204 wt.% FeO and demonstrates consistent performance across diverse lunar geological units. Applied to 806 orbital tracks (approximately pixels), covering more than 95% of the lunar surface, the pipeline produces a global FeO abundance map at 150 m per pixel resolution. These results demonstrate the potential of integrating multiscale wavelet representations with nonlinear feature learning to enable large-scale, geochemically constrained planetary mineral mapping.