The increasing demand for gold, coupled with persistently high market prices over the past decade, has driven a significant rise in small-scale gold production. The expansion of unregularized small-scale gold mines fuels environmental degradation and poses a risk to miners and mining communities. To promote sustainable mining practices, support reclamation initiatives and pave the way for understudying the impacts of mining on human and environmental resources, we presentSmallMinesDS, a dataset derived from multi-sensor satellite imagery covering five districts in southwestern Ghana in two time periods.SmallMinesDSprovides precise reference data for artisanal mining sites, enabling the development of machine learning models for timely, large-scale, and cost-effective monitoring. Notably, foundation models fine-tuned onSmallMinesDSachieve up to 75% intersection-over-union while maintaining a strong balance between minimizing false positives and negatives.

The classification of dominant leaf types, which distinguishes forests based on their leaf conditions, is beneficial for forest management and policymakers. This paper proposes a model based on U-Net to classify the land into non-tree areas, broadleaf forests, and coniferous forests. The dual-pol Sentinel-1 data from January, May, August, and October of 2018 were stacked as a time series. Due to the class imbalance issue, where the non-tree area category dominates (52.69%) the dataset, the model tends to be biased. Thus, re-weighting is introduced to balance the loss. We tested and compared two types of methods: class-aware and task-aware re-weighting. The results indicate that re-weighting effectively mitigates the class imbalance issue.

In this study, we examine the potential of several self-supervised deep learning models in predicting forest attributes and detecting forest changes using ESA Sentinel-1 and Sentinel-2 images. The performance of the proposed deep learning models is compared to established conventional machine learning approaches. Studied use-cases include mapping of forest disturbance (windthrown forests, snowload damages) using deep change vector analysis, forest height mapping using UNet+ based models, Momentum contrast and regression modeling. Study areas were represented by several boreal forest sites in Finland. Our results indicate that developed methods allow to achieve superior classification and prediction accuracies compared to traditional methodologies and mimimize the amount of necessary in-situ forestry data.

The availability of open-access satellite data and advancements in machine learning techniques has exhibited significant potential in crop yield prediction. In the context of large farming systems and county-level predictions, it is customary to rely on coarse-resolution satellite images. However, these images often lack the sufficient textural detail to accurately summarise spatial information. This research aims to evaluate the advantages of enhanced spatial resolution by conducting a comparative analysis between coarse-resolution, high-temporal-frequency MODIS data and relatively high-resolution, low-temporal-frequency Landsat data for predicting corn yield in the USA. We benchmark this comparison against several models in a spatial versus non-spatial input data context. Our results suggest that, the use of high-spatial resolution for county-level yield prediction in large farming systems is not beneficial and the models explored are unable to generalize well to drought-struck years.

Template protection is an issue of paramount importance for the design of secure and privacy-compliant biometric recognition systems. Template unlinkability, together with template irreversibility, is an essential requirement to properly guarantee template protection. In fact, it ensures that templates generated from the same trait, but used in different applications, cannot be linked to the same identity. This paper deals with the design of a system satisfying the unlinkability requirement. The robustness of the proposed solution is evaluated by exploiting methods stemming from the theory of stochastic optimization, as well as by using quantitative measures specifically proposed to characterize the unlinkability of biometric protection schemes. A case study using finger-vein biometrics is considered to test the proposed cryptosystem on non-ideal data. The proposed scheme guarantees 128 bits of security with acceptable false recognition rates in real-life conditions. Moreover, we provide guidelines to determine the parameters of the transformations to be applied to real biometric traits so as to ensure proper recognition, security, and unlinkability performance.

The AI4EO Hyperview challenge seeks machine learning methods that predict agriculturally relevant soil parameters (K, Mg, P2O5, pH) from airborne hyperspectral images. We present a hybrid model fusing Random Forest and K-nearest neighbor regressors that exploit the average spectral reflectance, as well as derived features such as gradients, wavelet coefficients, and Fourier transforms. The solution is computationally lightweight and improves upon the challenge baseline by 21.9%, with the first place on the public leaderboard. In addition, we discuss neural network architectures and potential future improvements.

In this letter, we propose a vein-based biometric verification system relying on deep learning. A novel approach consisting of a convolutional neural network (CNN), trained in a supervised manner, cascaded with an auto-encoder, trained in an unsupervised way, is here exploited. In more detail, a novel densely-connected convolutional autoencoder is here used on top of backbone CNNs. This architecture aims at increasing the discriminative capability of the features generated from hand vein patterns. Experimental tests on finger, palm, and dorsal veins show that the proposed approach leads to an improvement of the recognition rates with respect to the use of the sole CNNs for feature extraction. The achieved performance are superior to the current state of the art in vein biometric verification.

Finger-vein-based biometric recognition technology has recently attracted the attention of both academia and industry because of its robustness against presentation attacks and the convenience of the acquisition process. As a matter of fact, some contactless vein-based recognition systems have already been deployed and commercialized. However, they require the users to keep their hands still over the acquisition device for a few seconds to perform recognition. In this study, we release this constraint and allow users to have their finger vein patterns acquired on-the-fly. To accomplish this goal, we introduce an ad-hoc acquisition architecture capable of capturing the finger vein structure using an array of low-cost cameras, and we propose a recognition framework based on the use of convolutional and recurrent neural networks. To test the proposed approach we acquire a finger vein image dataset, in video format at four different exposure times, from 100 subjects. The obtained experimental results show that, even in a very challenging scenario, the proposed system guarantees high performance levels, up to 99.13% recognition accuracy over the collected dataset.