Search Results (16)

Simulating animal movement has long been a central focus of study in the area of wildlife behaviour studies. Conventional modelling methods have difficulties in accurately representing changes over time and space in the data, and they generally do not effectively use telemetry data. Thus, this paper introduces a new and innovative deep reinforcement learning technique known as AnimalEnvNet. This approach combines historical trajectory data and remote sensing images to create an animal agent using deep reinforcement learning techniques. It overcomes the constraints of conventional modelling approaches. We selected pandas as the subject of our research and carried out research using GPS trajectory data, Google Earth images, and Sentinel-2A remote sensing images. The experimental findings indicate that AnimalEnvNet reaches convergence during supervised learning training, attaining a minimal mean absolute error (MAE) of 28.4 m in single-step prediction when compared to actual trajectories. During reinforcement learning training, the agent has the capability to replicate animal locomotion for a maximum of 12 iterations, while maintaining an error margin of 1000 m. This offers a novel approach and viewpoint for mimicking animal behaviour. Full article

Global Positioning Systems (GPSs) can collect tracking data to remotely monitor livestock well-being and pasture use. Supervised machine learning requires behavioral observations of monitored animals to identify changes in behavior, which is labor-intensive. Our goal was to identify animal behaviors automatically without using human observations. We designed a novel framework using unsupervised learning techniques. The framework contains two steps. The first step segments cattle tracking data using state-of-the-art time series segmentation algorithms, and the second step groups segments into clusters and then labels the clusters. To evaluate the applicability of our proposed framework, we utilized GPS tracking data collected from five cows in a 1096 ha rangeland pasture. Cow movement pathways were grouped into six behavior clusters based on velocity (m/min) and distance from water. Again, using velocity, these six clusters were classified into walking, grazing, and resting behaviors. The mean velocity for predicted walking and grazing and resting behavior was 44, 13 and 2 min/min, respectively, which is similar to other research. Predicted diurnal behavior patterns showed two primary grazing bouts during early morning and evening, like in other studies. Our study demonstrates that the proposed two-step framework can use unlabeled GPS tracking data to predict cattle behavior without human observations. Full article

The Great Lakes (GL) wetlands support a variety of rare and endangered animal and plant species. Thus, wetlands in this region should be mapped and monitored using advanced and reliable techniques. In this study, a wetland map of the GL was produced using Sentinel-1/2 datasets within the Google Earth Engine (GEE) cloud computing platform. To this end, an object-based supervised machine learning (ML) classification workflow is proposed. The proposed method contains two main classification steps. In the first step, several non-wetland classes (e.g., Barren, Cropland, and Open Water), which are more distinguishable using radar and optical Remote Sensing (RS) observations, were identified and masked using a trained Random Forest (RF) model. In the second step, wetland classes, including Fen, Bog, Swamp, and Marsh, along with two non-wetland classes of Forest and Grassland/Shrubland were identified. Using the proposed method, the GL were classified with an overall accuracy of 93.6% and a Kappa coefficient of 0.90. Additionally, the results showed that the proposed method was able to classify the wetland classes with an overall accuracy of 87% and a Kappa coefficient of 0.91. Non-wetland classes were also identified more accurately than wetlands (overall accuracy = 96.62% and Kappa coefficient = 0.95). Full article

The synchronization of videos is an essential pre-processing step for multi-view reconstruction such as the image mosaic by UAV remote sensing; it is often solved with hardware solutions in motion capture studios. However, traditional synchronization setups rely on manual interventions or software solutions and only fit for a particular domain of motions. In this paper, we propose a self-supervised video synchronization algorithm that attains high accuracy in diverse scenarios without cumbersome manual intervention. At the core is a motion-based video synchronization algorithm that infers temporal offsets from the trajectories of moving objects in the videos. It is complemented by a self-supervised scene decomposition algorithm that detects common parts and their motion tracks in two or more videos, without requiring any manual positional supervision. We evaluate our approach on three different datasets, including the motion of humans, animals, and simulated objects, and use it to build the view panorama of the remote sensing field. All experiments demonstrate that the proposed location-based synchronization is more effective compared to the state-of-the-art methods, and our self-supervised inference approaches the accuracy of supervised solutions, while being much easier to adapt to a new target domain. Full article

Wetlands provide many benefits, such as water storage, flood control, transformation and retention of chemicals, and habitat for many species of plants and animals. The ongoing degradation of wetlands in the Great Lakes basin has been caused by a number of factors, including climate change, urbanization, and agriculture. Mapping and monitoring wetlands across such large spatial and temporal scales have proved challenging; however, recent advancements in the accessibility and processing efficiency of remotely sensed imagery have facilitated these applications. In this study, the historical Landsat archive was first employed in Google Earth Engine (GEE) to classify wetlands (i.e., Bog, Fen, Swamp, Marsh) and non-wetlands (i.e., Open Water, Barren, Forest, Grassland/Shrubland, Cropland) throughout the entire Great Lakes basin over the past four decades. To this end, an object-based supervised Random Forest (RF) model was developed. All of the produced wetland maps had overall accuracies exceeding 84%, indicating the high capability of the developed classification model for wetland mapping. Changes in wetlands were subsequently assessed for 17 time intervals. It was observed that approximately 16% of the study area has changed since 1984, with the highest increase occurring in the Cropland class and the highest decrease occurring in the Forest and Marsh classes. Forest mostly transitioned to Fen, but was also observed to transition to Cropland, Marsh, and Swamp. A considerable amount of the Marsh class was also converted into Cropland. Full article

Coastal aquaculture is an important supply of animal proteins for human consumption, which is expanding globally. Meanwhile, extensive aquaculture may increase nutrient loadings and environmental concerns along the coast. Accurate information on aquaculture pond location is essential for coastal management. Traditional methods use morphological parameters to characterize the geometry of surface waters to differentiate artificially constructed conventional aquaculture ponds from other water bodies. However, there are other water bodies with similar morphology (e.g., saltworks, rice fields, and small reservoirs) that are difficult to distinguish from aquaculture ponds, causing a lot of omission/commissioning errors in areas with complex land-use types. Here, we develop an extraction method with shape and water quality parameters to map aquaculture ponds, including three steps: (1) Sharpen normalized difference water index to detect and binarize water pixels by the Otsu method; (2) Connect independent water pixels into water objects through the four-neighbor connectivity algorithm; and (3) Calculate the shape features and water quality features of water objects and input them into the classifier for supervised classification. We selected eight sites along the coast of China to evaluate the accuracy and generalization of our method in an environment with heterogeneous pond morphology and landscape. The results showed that six transfer characteristics including water quality characteristics improved the accuracy of distinguishing aquaculture ponds from salt pans, rice fields, and wetland parks, which typically had F1 scores > 85%. Our method significantly improved extraction efficiency on average, especially when aquaculture ponds are mixed with other morphological similar water bodies. Our identified area was in agreement with statistics data of 12 coastal provinces in China. In addition, our approach can effectively improve water objects when high-resolution remote sensing images are unavailable. This work was applied to open-source remote sensing imagery and has the potential to extract long-term series and large-scale aquaculture ponds globally. Full article

The Prokopos Lagoon is part of the Kotychi Strofilias National Wetlands Park, which is supervised by the Ministry of Environment, Energy and Climate Change of Greece. The lagoon is situated at the northwestern coast of the Peloponnese and is protected by the Ramsar Convention. It is an important ecosystem with ecological services providing habitats for many plants and animals and essential goods and services for humans as well. No previous relevant studies for the wider wetland area are available, and given that lagoons are important ecosystems, their diachronic evolution should be under constant monitoring. Using remote sensing techniques in Geographic Information System (GIS) environment, alterations in critical parameters could be measured and applied for the protection of the area. The present study examines the spatiotemporal changes of the water extent of the Prokopos Lagoon, estimating landscape metrics and several morphometric parameters and indices related to the geomorphological features of the lagoon for the 1945–2021 period. Moreover, the adjacent shoreline was studied for each past decade evolution from 1945 to present, and it is discussed to whether there is a relationship between shoreline changes and the lagoon. High resolution satellite images and air photos at scale 1:30,000 were used to digitize the shorelines and the polygons of the lagoon’s surface. Linear Regression Rates (LRR), Net Shoreline Movement (NSM), End Point Rate (EPR) and Shoreline Change Envelope (SCE) provided by the Digital Shoreline Analysis System (DSAS) were used to determine the changes. Finally, future shoreline positions for 2021 and 2031 are estimated, while based on statistic models, we found that in the coastal area, the erosion–accretion cycle is predicted to be completed in 2031, after almost 86 years since 1945. Full article

Camera traps deployed in remote locations provide an effective method for ecologists to monitor and study wildlife in a non-invasive way. However, current camera traps suffer from two problems. First, the images are manually classified and counted, which is expensive. Second, due to manual coding, the results are often stale by the time they get to the ecologists. Using the Internet of Things (IoT) combined with deep learning represents a good solution for both these problems, as the images can be classified automatically, and the results immediately made available to ecologists. This paper proposes an IoT architecture that uses deep learning on edge devices to convey animal classification results to a mobile app using the LoRaWAN low-power, wide-area network. The primary goal of the proposed approach is to reduce the cost of the wildlife monitoring process for ecologists, and to provide real-time animal sightings data from the camera traps in the field. Camera trap image data consisting of 66,400 images were used to train the InceptionV3, MobileNetV2, ResNet18, EfficientNetB1, DenseNet121, and Xception neural network models. While performance of the trained models was statistically different (Kruskal–Wallis: Accuracy H(5) = 22.34, p < 0.05; F1-score H(5) = 13.82, p = 0.0168), there was only a 3% difference in the F1-score between the worst (MobileNet V2) and the best model (Xception). Moreover, the models made similar errors (Adjusted Rand Index (ARI) > 0.88 and Adjusted Mutual Information (AMU) > 0.82). Subsequently, the best model, Xception (Accuracy = 96.1%; F1-score = 0.87; F1-Score = 0.97 with oversampling), was optimized and deployed on the Raspberry Pi, Google Coral, and Nvidia Jetson edge devices using both TenorFlow Lite and TensorRT frameworks. Optimizing the models to run on edge devices reduced the average macro F1-Score to 0.7, and adversely affected the minority classes, reducing their F1-score to as low as 0.18. Upon stress testing, by processing 1000 images consecutively, Jetson Nano, running a TensorRT model, outperformed others with a latency of 0.276 s/image (s.d. = 0.002) while consuming an average current of 1665.21 mA. Raspberry Pi consumed the least average current (838.99 mA) with a ten times worse latency of 2.83 s/image (s.d. = 0.036). Nano was the only reasonable option as an edge device because it could capture most animals whose maximum speeds were below 80 km/h, including goats, lions, ostriches, etc. While the proposed architecture is viable, unbalanced data remain a challenge and the results can potentially be improved by using object detection to reduce imbalances and by exploring semi-supervised learning. Full article

Human activities in the sea, such as intensive fishing and exploitation of offshore wind farms, may impact negatively on the marine mega fauna. As an attempt to control such impacts, surveying, and tracking of marine animals are often performed on the sites where those activities take place. Nowadays, thank to high resolution cameras and to the development of machine learning techniques, tracking of wild animals can be performed remotely and the analysis of the acquired images can be automatized using state-of-the-art object detection models. However, most state-of-the-art detection methods require lots of annotated data to provide satisfactory results. Since analyzing thousands of images acquired during a flight survey can be a cumbersome and time consuming task, we focus in this article on the weakly supervised detection of marine animals. We propose a modification of the patch distribution modeling method (PaDiM), which is currently one of the state-of-the-art approaches for anomaly detection and localization for visual industrial inspection. In order to show its effectiveness and suitability for marine animal detection, we conduct a comparative evaluation of the proposed method against the original version, as well as other state-of-the-art approaches on two high-resolution marine animal image datasets. On both tested datasets, the proposed method yielded better F1 and recall scores (75% recall/41% precision, and 57% recall/60% precision, respectively) when trained on images known to contain no object of interest. This shows a great potential of the proposed approach to speed up the marine animal discovery in new flight surveys. Additionally, such a method could be adopted for bounding box proposals to perform faster and cheaper annotation within a fully-supervised detection framework. Full article

High or variable ambient temperature can affect thermal regulation in livestock, but few studies have studied thermal variability during air and road transport, partly due to the lack of tools to compare thermal data from a long time series over periods of different duration. In this study, we recorded the ear skin temperature (EST) of 11 Duroc breeder pigs (7 females and 4 males) during commercial intercontinental transport from Canada to Spain, which included both road and aircraft travel and lasted 65 h. The EST was measured using a logger placed inside the left ear. Phase space diagrams EST, that is EST time series vs. itself delayed in time, were used to quantify the variability of the time-temperature series based on the areas that included all the points in the phase space. Phase space areas were significantly higher for all the animals during air travel, almost doubling that of road transport. Using the phase spaces, we identified an event during air transport that lasted 57 min, leading to a general decrease in EST by 8 °C, with respect to the average EST (34.1 °C). We also found that thermal variability was more stable in males (F = 20.81, p = 0.0014), which were also older and heavier. Full article

Land use and land cover change (LUCC) is an important driver of ecosystem function and services. Thus, LUCC analysis may lay foundation for landscape planning, conservation and management. It is especially true for alpine landscapes, which are more susceptible to climate changes and human activities. However, the information on LUCC in sacred landscape is limited, which will hinder the landscape conservation and development. We chose Kailash Sacred Landscape in China (KSL-China) to investigate the patterns and dynamics of LUCC and the driving forces using remote sensing data and meteorological data from 1990 to 2008. A supervised classification of land use and land cover was established based on field survey. Rangelands presented marked fluctuations due to climatic warming and its induced drought, for example, dramatic decreases were found in high- and medium-cover rangelands over the period 2000–2008. And recession of most glaciers was also observed in the study period. Instead, an increase of anthropogenic activities accelerated intensive alteration of land use, such as conversion of cropland to built-up land. We found that the change of vegetation cover was positively correlated with growing season precipitation (GSP). In addition, vegetation cover was substantially reduced along the pilgrimage routes particularly within 5 km of the routes. The findings of the study suggest that climatic warming and human disturbance are interacted to cause remarkable LUCC. Tourism development was responsible land use change in urban and pilgrimage routes. This study has important implications for landscape conservation and ecosystem management. The reduction of rangeland cover may decrease the rangeland quality and pose pressure for the carrying capacity of rangelands in the KSL-China. With the increasing risk of climate warming, rangeland conservation is imperative. The future development should shift from livestock-focus animal husbandry to service-based ecotourism in the sacred landscape. Full article

Kernel-based home range models are widely-used to estimate animal habitats and develop conservation strategies. They provide a probabilistic measure of animal space use instead of assuming the uniform utilization within an outside boundary. However, this type of models estimates the home ranges from animal relocations, and the inadequate locational data often prevents scientists from applying them in long-term and large-scale research. In this paper, we propose an end-to-end deep learning framework to simulate kernel home range models. We use the conditional adversarial network as a supervised model to learn the home range mapping from time-series remote sensing imagery. Our approach enables scientists to eliminate the persistent dependence on locational data in home range analysis. In experiments, we illustrate our approach by mapping the home ranges of Bar-headed Geese in Qinghai Lake area. The proposed framework outperforms all baselines in both qualitative and quantitative evaluations, achieving visually recognizable results and high mapping accuracy. The experiment also shows that learning the mapping between images is a more effective way to map such complex targets than traditional pixel-based schemes. Full article

Estimating animal populations by direct counting is an essential component of wildlife conservation and management. However, conventional approaches (i.e., ground survey and aerial survey) have intrinsic constraints. Advances in image data capture and processing provide new opportunities for using applied remote sensing to count animals. Previous studies have demonstrated the feasibility of using very high resolution multispectral satellite images for animal detection, but to date, the practicality of detecting animals from space using panchromatic imagery has not been proven. This study demonstrates that it is possible to detect and count large mammals (e.g., wildebeests and zebras) from a single, very high resolution GeoEye-1 panchromatic image in open savanna. A novel semi-supervised object-based method that combines a wavelet algorithm and a fuzzy neural network was developed. To discern large mammals from their surroundings and discriminate between animals and non-targets, we used the wavelet technique to highlight potential objects. To make full use of geometric attributes, we carefully trained the classifier, using the adaptive-network-based fuzzy inference system. Our proposed method (with an accuracy index of 0.79) significantly outperformed the traditional threshold-based method (with an accuracy index of 0.58) detecting large mammals in open savanna. Full article

Wetlands are some of the most important ecosystems on Earth. They play a key role in alleviating floods and filtering polluted water and also provide habitats for many plants and animals. Wetlands also interact with climate change. Over the past 50 years, wetlands have been polluted and declined dramatically as land cover has changed in some regions. Remote sensing has been the most useful tool to acquire spatial and temporal information about wetlands. In this paper, seven types of sensors were reviewed: aerial photos coarse-resolution, medium-resolution, high-resolution, hyperspectral imagery, radar, and Light Detection and Ranging (LiDAR) data. This study also discusses the advantage of each sensor for wetland research. Wetland research themes reviewed in this paper include wetland classification, habitat or biodiversity, biomass estimation, plant leaf chemistry, water quality, mangrove forest, and sea level rise. This study also gives an overview of the methods used in wetland research such as supervised and unsupervised classification and decision tree and object-based classification. Finally, this paper provides some advice on future wetland remote sensing. To our knowledge, this paper is the most comprehensive and detailed review of wetland remote sensing and it will be a good reference for wetland researchers. Full article

The trend of land cover (LC) and land cover change (LCC), both in time and space, was investigated at the Simen Mountains National Park (SMNP), a World Heritage Site located in northern Ethiopia, between 1984 and 2003 using Geographical Information System (GIS) and remote sensing (RS). The objective of the study was to generate spatially and temporally quantified information on land cover dynamics, providing the basis for policy/decision makers and resource managers to facilitate biodiversity conservation, including wild animals. Two satellite images (Landsat TM of 1984 and Landsat ETM+ of 2003) were acquired and supervised classification was used to categorize LC types. Ground Control Points were obtained in field condition for georeferencing and accuracy assessment. The results showed an increase in the areas of pure forest (Erica species dominated) and shrubland but a decrease in the area of agricultural land over the 20 years. The overall accuracy and the Kappa value of classification results were 88 and 85%, respectively. The spatial setting of the LC classes was heterogeneous and resulted from the biophysical nature of SMNP and anthropogenic activities. Further studies are suggested to evaluate the existing LC and LCC in connection with wildlife habitat, conservation and management of SMNP. Full article