TRIM4Post-Mining is a H2020/RFCS-funded project that brings together a consortium of European experts from industry and academia to develop an integrated information modelling system. This is designed to support decision making and planning during the transition from coal exploitation to a revitalized post-mining landscape, enabling infrastructure development for agricultural and industrial utilization, and contributing to the recovery of energy and materials from coal mining dumps. The smart system will be founded upon a high-resolution spatiotemporal database, utilizing state-of-the-art multi-scale and multi-sensor monitoring technologies that characterize dynamic processes in coal waste dumps related to timely, dependent deformation and geochemical processes. It will integrate efficient methods for operational and post-mining monitoring, comprehensive spatiotemporal data analytics, feature extraction, and predictive modelling; this will allow for the identification of potential contamination areas and the forecasting of geotechnical risks and ground conditions. For the interactive exploration of alternative land-use planning scenarios—in terms of residual risks, technical feasibility, environmental and social impact, and affordability—up-to-date data and models will be embedded in an interactive planning system based on Virtual Reality and Augmented Reality technology, forming a TRIM—a Transition Information Modelling System. This contribution presents the conceptual approach and main constituents, and describes the state-of-the-art and detailed anticipated methodological approach for each of the constituents. This is supported by the presentation of the first results and a discussion of future work. An anticipated second contribution will focus on the main findings, technology readiness and a discussion of future work.

In terms of its history and complexity, the Lugau/Oelsnitz mining area is a representative example of many hard coal fields in Europe. The special characteristic, however, is the low water inflow and the associated long flooding process with corresponding low and long-ongoing ground movements. In order to ensure the long-term monitoring of ground movements in the future, an adapted and cost-effective concept based on modern methods should be implemented. The today widely used radar interferometry, is well established as a method but the results offer many possibilities for interpretation, which one should be aware of in order to derive reliable information. Presented are the results of a complex interferometric evaluation, based on Sentinel-1 data from different orbits, and an analysis of the spatiotemporal characteristic of ground movements. The focus of this paper is a detailed presentation of the workflow and an application-related interpretation of the results. The pool of methods used includes radar interferometry, but also spatiotemporal analysis and modeling. The overall objective of this comprehensive case study is to present the possibilities but also the limitations of the application of radar interferometry and to provide a perspective for future monitoring in post-mining areas.

Mobile GIS allows users who work in the field to acquire, edit, update, store, display and analyse data. It combines modern technologies such as mobile devices (tablet, smartphone), software (applications in Android and iOS), location of a point / place using GNSS transmitter and providing wireless connectivity via the internet. An important step in any scientific research should be the verification of the obtained results, which can be done by using a modern tool such as mobile GIS. In this article the characteristics of mobile GIS will be presented as well as selected examples of modern research carried out at universities in Germany: Technische Hochschule Georg Agricola University (THGA), Technical University Bergakademie Freiberg (TUBAF) and Poland – Wrocław University of Science and Technology (WUST).

The paper presents some recent developments on object-based change detection and classification. In detail, the following algorithms were implemented either as Matlab or IDL programmes or as plug-ins for Definiens Developer: i) object-based change detection: segmentation of bitemporal datasets, change detection using the Multivariate Alteration Detection1 based on object features; ii) object features and object feature extraction: moment invariants, automated extraction of object features using Bayesian statistics; iii) object-based classification by neural networks: FFN and Class- dependent FFN using five different learning algorithms. The paper introduces the methodologies, describes the implementation and gives some examples results on the application.

Droughts are among the most critical natural hazards affecting agricultural productivity, water resources, and food security worldwide, with climate change intensifying their frequency and severity. Accurate monitoring and forecasting of drought events are therefore essential for effective risk management and sustainable resource planning. In this study, we systematically evaluated the performance of four machine learning approaches—Support Vector Regression (SVR), Random Forest (RF), K-Nearest Neighbor (kNN), and Linear Regression (LR)—for tracking and predicting the Standardized Precipitation Index (SPI) at multiple temporal scales (1, 3, 6, 9, 12, 18, and 24 months). We utilized a century-long precipitation dataset from a meteorological station in south-eastern Tunisia to compute SPI values and forecast drought occurrences. The Mann–Kendall trend test was applied to assess the presence of significant trends in the monthly SPI series. The results revealed upward trends in SPI 12, SPI 18, and SPI 24, indicating decreasing drought severity over longer time scales, while SPI 1, SPI 3, SPI 6, and SPI 9 did not exhibit statistically significant trends. Model efficacy was assessed using a suite of statistical metrics: mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and the correlation coefficient (R). While all models exhibited robust predictive performance, Support Vector Regression (SVR) proved superior, achieving the highest accuracy across both short- and long-term time horizons. These findings highlight the effectiveness of machine learning approaches in drought forecasting and provide critical insights for regional water resource management, agricultural planning, and ecological sustainability.