Background: The ability to automatically count animals is important to design appropriate environmental policies and to monitor their populations in relation to biodiversity and maintain balance among species. Out of all living mammals on Earth, 60% are livestock, 36% humans, and only 4% are animals that live in the wild. In a relatively short period, development of human civilization caused a loss of 83% of wildlife and 50% of plants. The rate of species extinction is accelerating. Traditional wildlife surveys provide rough population estimates. However, emerging technologies, such as aerial photography, allow to perform large-scale surveys in a short period of time with high accuracy. In this paper, we propose the use of computer vision, through deep learning (DL) architecture, together with aerial photography and density maps, to count the population of Steller sea lions and African elephants with high precision. Results: We have trained two deep learning models, a basic UNet without any feature extractor (Model-1) and another with the EfficientNet-B5 feature extractor (Model-2). We measured the model’s prediction accuracy, using Root Mean Square Error (RMSE) for the predicted and actual animal count. The results showed an RMSE of 1.88 and 0.60 to count Steller sea lions and African elephants, respectively, regardless of complex background, different illumination conditions, heavy overlapping and occlusion of the animals. Conclusions: Our proposed solution performed very well in the counting prediction problem, with relatively low training parameters and minimum annotation. The approach adopted, combining DL and density maps, provided better results than state-of-art deep learning models used for counting, indicating that the proposed method has the potential to be used more widely in large-scale wildlife surveying projects and initiatives.
Despite the plethora of successful super-resolution (SR) reconstruction (SRR) models applied to natural images, their application to remote sensing imagery tends to produce poor results. Remote sensing imagery is often more complicated than natural images, has its peculiarities such as being of lower resolution, contains noise, and often depicts large textured surfaces. As a result, applying nonspecialized SRR models like the enhanced SR generative adversarial network (ESRGAN) on remote sensing imagery results in artifacts and poor reconstructions. To address these problems, we propose a novel strategy for enabling an SRR model to output realistic remote sensing images: instead of relying on feature-space similarities as a perceptual loss, the model considers pixel-level information inferred from the normalized digital surface model (nDSM) of the image. This allows the application of better-informed updates during the training of the model which sources from a task (elevation map inference) that is closely related to remote sensing. Nonetheless, the nDSM auxiliary information is not required during production, i.e., the model infers an SR image without additional data. We assess our model on two remotely sensed datasets of different spatial resolutions that also contain the DSMs of the images: the Data Fusion 2018 Contest (DFC2018) dataset and the dataset containing the national LiDAR flyby of Luxembourg. We compare our model with ESRGAN, and we show that it achieves better performance and does not introduce any artifacts in the results. In particular, the results for the high-resolution DFC2018 dataset are realistic and almost indistinguishable from the ground-truth images.
Global Earth observation is becoming increasingly important in understanding and addressing critical aspects of life on our planet, including environmental issues, natural disasters, sustainable development, and others. Finding similarities in landscapes may provide useful information regarding applying contiguous policies, by making similar decisions or learning from best practices for events and occurrences that previously occurred in similar landscapes in the past. However, current applications of similar landscape retrieval are limited by a moderate performance and the need for time-consuming and costly annotations. We propose splitting the similar landscape retrieval task into a set of smaller tasks that aim to identify individual concepts inherent to satellite images. Our approach relies on several models trained using unsupervised representation learning on Google Earth images to identify these concepts. We show the efficacy of matching individual concepts for retrieving landscape(s) similar to a user-selected satellite image of the geographical territory of the Republic of Cyprus. Our results demonstrate the benefits of breaking up the landscape similarity task into individual concepts closely related to remote sensing, instead of applying a single model targeting all underlying concepts.
Monitoring species distribution is vital for conservation efforts, enabling the assessment of environmental impacts and the development of effective preservation strategies. Traditional data collection methods, including citizen science, offer valuable insights but remain limited in coverage and completeness. Species Distribution Modelling (SDM) helps address these gaps by using occurrence data and environmental variables to predict species presence across large regions. In this study, we enhance SDM accuracy for frogs (Anura) by applying deep learning and data imputation techniques using data from the "EY - 2022 Biodiversity Challenge." Our experiments show that data balancing significantly improved model performance, reducing the Mean Absolute Error (MAE) from 189 to 29 in frog counting tasks. Feature selection identified key environmental factors influencing occurrence, optimizing inputs while maintaining predictive accuracy. The multimodal ensemble model, integrating land cover, NDVI, and other environmental inputs, outperformed individual models and showed robust generalization across unseen regions. The fusion of image and tabular data improved both frog counting and habitat classification, achieving 84.9% accuracy with an AUC of 0.90. This study highlights the potential of multimodal learning and data preprocessing techniques such as balancing and imputation to improve predictive ecological modeling when data are sparse or incomplete, contributing to more precise and scalable biodiversity monitoring.