Three studies were conducted in collaboration with the Helmholtz Institute Freiberg for Resource Technology, an institute of the Helmholtz-Zentrum Dresden-Rossendorf (HZDR). The researchers advocate for the ethically guided use of artificial intelligence (AI) for Earth observation, particularly in environmental protection and disaster prevention. They have also developed an AI-supported model that incorporates data obtained through remote sensing, which may represent a significant advancement for the Earth observation community. 

The studies have been published on the arXiv preprint server and in IEEE Transactions on Pattern Analysis and Machine Intelligence. The title of the first study is “MineNetCD—A Benchmark for Global Mining Change Detection on Remote Sensing Imagery.” 

This research, led by an international research group including the Helmholtz Institute Freiberg for Resource Technology (HIF), focuses on the exploration and monitoring of mining areas using remote sensing images. 

The newly developed dataset, "MineNetCD," is based on over 70,000 bitemporal high-resolution remote sensing image pairs from 100 mining sites worldwide. These images, together with the proposed unified change detection framework that integrates over 13 advanced change detection models, enable a detailed inventory and analysis of mining-induced changes. 

According to Professor Pedram Ghamisi, Head of the Machine Learning group in the Exploration Department at HIF, this represents the first global benchmark for monitoring mining activities. The algorithms developed are powerful tools for researchers and developers monitoring global mining activities. 

The ChangeFFT Model

A key component of the study is the ChangeFFT model, which provides mining planners with a specific measurement method—the Fast Fourier Transformation—for utilizing remote sensing images. This allows for a detailed analysis of critical spectral components and the detection of changes down to the pixel level, achieving higher accuracy and efficiency in processing large datasets. 

Professor Ghamisi remarked that the open access to MineNetCD and the ChangeFFT model is intended to support the global research community and contribute to the development of sustainable mining practices. 

Ensuring Responsible AI 

Among the new possibilities for using remote sensing images in mining is the increasing application of Artificial Intelligence (AI). In the second study, titled "Responsible AI for Earth Observation," an international research team emphasizes the need to incorporate ethical and responsible practices. 

Professor Pedram Ghamisi, who played a leading role in the international study, explains that AI has the potential to achieve significant advances in the analysis of Earth observation data, particularly in areas such as climate change, deforestation, and natural disasters. 

However, the use of these technologies also carries risks, such as algorithmic biases, lack of transparency, and the potential to exacerbate social inequalities. The researchers highlight the importance of techniques to mitigate such biases and argue that the AI models used must be not only powerful but also socially and ethically interpretable and accountable. The study advocates for the prioritized use of transparent and understandable AI systems.

SpectralGPT for Remote Sensing

ChatGPT is known by many as an AI-supported communication platform. A similar trained platform now exists for remote sensing images, called SpectralGPT. This was presented in a study titled "SpectralGPT: Spectral Remote Sensing Foundation Model," conducted by an international research group in collaboration with the HIF. SpectralGPT is the first universal remote-sensing foundation model, trained using over a million images of varying sizes, resolutions, time series, and regions in a progressive training fashion. This approach enables the full utilization of extensive remote sensing big data and is tested across a variety of vision-related tasks.

According to Professor Ghamisi, the focus of AI algorithms has shifted between being model-centric and data-centric over time. However, focusing on only one aspect is insufficient. Instead, there must be a balanced emphasis on both data quality and model innovation, which would bring AI experts and domain experts together. In his opinion, these models are a step toward the long-standing dream in the Earth observation community of addressing a variety of applications using a single model.

Phys Org