Article
Environmental Sciences
Haihui You, Juntao Gu, Weipeng Jing
Summary: This study proposes a multi-label classification model for multi-source remote sensing images that combines dense convolution and an attention mechanism. The model enhances feature extraction and classification accuracy by adding fusion channel attention and a spatial attention mechanism, as well as replacing the softmax activation function with the sigmoid activation function.
Review
Ecology
Theo Michelot, Natasha J. Klappstein, Jonathan R. Potts, John Fieberg
Summary: Step selection functions are flexible statistical models used to describe animal movement and habitat preferences. However, there has been confusion in the literature regarding model flexibility and interpretation. In this review, a coherent framework for model formulation and inference technique is presented using numerical integration and maximum likelihood estimation.
METHODS IN ECOLOGY AND EVOLUTION
(2023)
Article
Engineering, Environmental
Michael O. Levin, Elizabeth L. Kalies, Emma Forester, Elizabeth L. A. Jackson, Andrew H. Levin, Caitlin Markus, Patrick F. McKenzie, Jared B. Meek, Rebecca R. Hernandez
Summary: By 2050, the United States could generate up to 45% of its electricity using solar energy technology, which may require converting over 40,000 km(2) of land into large-scale solar energy production facilities. Little is known about the impact of such development on animal movement. This study uses spatial projections to assess the potential overlap between solar energy development and land important for animal movement, finding that there could be a substantial overlap, especially in areas important for migration and climate change-induced movement.
ENVIRONMENTAL SCIENCE & TECHNOLOGY
(2023)
Article
Biodiversity Conservation
Rehana Rasool, Abida Fayaz, Mifta ul Shafiq, Harmeet Singh, Pervez Ahmed
Summary: The study focuses on the changes in Land Use and Land Cover (LULC) in the Southern part of Kashmir Himalaya over a 27-year period. It finds that while cropland agriculture decreased the most (-5%), economically beneficial horticulture increased the most (+4.29%) during the study period. The changes in LULC are driven by various forces such as natural, demographic, and economic factors, resulting in pressures on land and environmental impacts. This study emphasizes the need for strict land use planning in Kashmir Himalayas to ensure food security and sustainability in the ecologically fragile environment. Understanding the complex interactions between human society and the environment is crucial for managing these complex systems.
ECOLOGICAL INDICATORS
(2021)
Review
Environmental Sciences
Worku Nega, Abel Balew
Summary: This study investigates the relationship between land use land cover (LULC) and land surface temperature (LST) using remote sensing data. The analysis of 100 studies reveals that built-up land has the highest LST, followed by bare land, while snow cover has the lowest LST and waterbodies have a lower LST compared to vegetation cover.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Biodiversity Conservation
S. Balouch, D. A. Driscoll, A. Naseer, M. Rais, T. S. Doherty
Summary: Agriculture poses a significant threat to biodiversity globally, but its impact on animal movement remains poorly understood. This study investigated the effect of landscape composition on the movements of the oriental garden lizard in agricultural landscapes in Pakistan. The results showed that tree patches were preferred by the lizards and that movement rates were higher when animals moved between different land cover types. The study also highlighted the importance of maintaining tree cover and field margins to promote wildlife conservation in agricultural landscapes.
ANIMAL CONSERVATION
(2022)
Article
Ecology
M. Salvatori, J. De Groeve, E. van Loon, B. De Baets, N. Morellet, S. Focardi, N. C. Bonnot, B. Gehr, M. Griggio, M. Heurich, M. Kroeschel, A. Licoppe, P. Moorcroft, L. Pedrotti, J. Signer, N. Van de Weghe, F. Cagnacci
Summary: The choice of geographic layers has an effect on the assessment of diel forest use by large herbivores. Inconsistent classification of forest or open habitat was found in approximately 20% of GPS locations within smaller habitat units. Both red and roe deer used forests more during the day than at night, and this pattern was more evident with Tree Cover Density layer.
Article
Multidisciplinary Sciences
Aline Giroux, Zaida Ortega, Luiz Gustavo Rodrigues Oliveira-Santos, Nina Attias, Alessandra Bertassoni, Arnaud Leonard Jean Desbiez
Summary: Research on giant anteaters in Brazilian savannah found that male individuals tend to have more intensive space use and larger home range compared to females with similar body mass, reflecting different strategies in resource acquisition. Both males and females increase their home range size with increasing body mass, but the scaling of intensity of space use differs between them, suggesting distinct search strategies for resources based on sex. Additionally, decreasing forest cover within their home ranges leads giant anteaters to increase their home range size, possibly to ensure access to thermal shelters as habitat quality declines. Effective management strategies should consider the integration of both intrinsic and environmental factors influencing animal movement to address the changing landscapes and climate conditions.
Article
Computer Science, Information Systems
Dongwei Li, Shuliang Wang, Qiang He, Yun Yang
Summary: Remote sensing image classification for land cover maps is vital, and the proposed cost-effective framework can significantly improve computational efficiency, leading to substantial savings for governments and related fields.
JOURNAL OF CLOUD COMPUTING-ADVANCES SYSTEMS AND APPLICATIONS
(2022)
Article
Environmental Sciences
Junrui Zhang, Zhitao Zhang, Junying Chen, Haiying Chen, Jiming Jin, Jia Han, Xintao Wang, Zhishuang Song, Guangfei Wei
Summary: This study investigated the impact of Fractional Vegetation Cover (FVC) on soil salinization using satellite remote sensing in Inner Mongolia. The results showed that classifying FVC improved the stability and predictive ability of the models, with Cubist performing the best, followed by ELM and PLSR. Optimal inversion models were constructed for different FVC categories and depths, providing valuable references for soil salinization prevention and agricultural production in the study area.
LAND DEGRADATION & DEVELOPMENT
(2021)
Article
Environmental Sciences
Solmaz Fathololoumi, Mohammad Karimi Firozjaei, Huijie Li, Asim Biswas
Summary: This study aims to improve the accuracy of land cover/land use classification by fusing different surface biophysical features and combining land cover maps from different scenarios. The results demonstrate that the fusion-based method significantly increases the overall accuracy of land cover/land use classification.
SCIENCE OF THE TOTAL ENVIRONMENT
(2022)
Article
Environmental Sciences
Yuan Yao, Yee Leung, Tung Fung, Zhenfeng Shao, Jie Lu, Deyu Meng, Hanchi Ying, Yu Zhou
Summary: This paper analyzes the differences between traditional remote sensing data and continuous multi-angle remote sensing (CMARS) data, highlighting the advantages of using CMARS data for classification. Real-life experiments show the superiority of CMARS data over traditional data in classification, with an increase in overall accuracy of up to about 9%. The research also explores the advantages and disadvantages of utilizing CMARS data directly and the potential for better utilization through the extraction of key features characterizing spectral reflectance variations.
Article
Forestry
Ying Ding, Huihui Feng, Bin Zou
Summary: This study summarizes the impact of land use and cover change (LUCC) on hydrological processes. Remote sensing technology provides continuous spatial data on land cover and hydrological variables. The effects of LUCC on hydrological processes can be evaluated using correlation analysis, multiple regression methods, experimental watershed approaches, and trajectory-based approaches. However, quantitatively separating the actual components of the influence of LUCC is challenging due to the complexity of geographical systems.
Article
Geochemistry & Geophysics
Yilang Shen, Jingzhong Li, Rong Zhao, Fengfeng Han
Summary: In this study, a superpixel-based land cover mapping method for remote sensing images is proposed, which can more effectively achieve multiresolution mapping by considering the geometric, topologic, and semantic characteristics of land parcels.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geography, Physical
Burak Ekim, Elif Sertel
Summary: Utilizing three different Deep Neural Network Ensemble methods can improve performance in remote sensing image classification tasks and increase accuracy. This approach enhances the generalizability of the models, generates more robust and generalizable outcomes, and promotes the widespread use of the method.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2021)
Article
Green & Sustainable Science & Technology
Tsegaye T. Gatiso, Lars Kulik, Mona Bachmann, Aletta Bonn, Lukas Boesch, Dustin Eirdosh, Andreas Freytag, Susan Hanisch, Marco Heurich, Tenekwetche Sop, Karsten Wesche, Marten Winter, Hjalmar S. Kuehl
Summary: Despite favorable socio-economic context and high conservation efforts, protected areas have limited effectiveness in halting biodiversity loss. Increasing conservation efforts may be necessary, but the diminishing marginal returns principle implies that even greater efforts and resources would be needed as protected areas approach zero biodiversity loss. Adopting core design principles that consider the social-ecological contexts of protected areas could help overcome the observed hurdles of limited effectiveness and better integrate them into sustainable development efforts.
NATURE SUSTAINABILITY
(2022)
Article
Environmental Sciences
Fabio Weiss, Frank Uwe Michler, Benjamin Gillich, Joerg Tillmann, Simone Ciuti, Marco Heurich, Siegfried Rieger
Summary: This study investigates the influence of herded sheep and goats on red deer spatial behavior. The findings show that red deer use grazed areas less during conservation grazing, and this effect persists up to 21 days after conservation grazing ends. Habitat selection of red deer is also affected up to 3000 meters away from the conservation grazing sites, with no signs of habituation or adaption.
ENVIRONMENTAL MANAGEMENT
(2022)
Article
Biodiversity Conservation
Hendrik Bluhm, Tom A. A. Diserens, Thomas Engleder, Kaja Heising, Marco Heurich, Tomas Janik, Miloslav Jirku, Daniel Klich, Hannes J. J. Koenig, Rafal Kowalczyk, Dries Kuijper, Weronika Maslanko, Frank-Uwe Michler, Wiebke Neumann, Julian Oeser, Wanda Olech, Kajetan Perzanowski, Miroslaw Ratkiewicz, Dusan Romportl, Martin Salek, Tobias Kuemmerle
Summary: This study aimed to assess the opportunities and limitations for range expansions of European bison and moose in Central Europe. It found widespread suitable habitats for these two species, but also identified human pressure and natural barriers that restrict their recolonization. Conservation measures restoring connectivity are needed to allow these large herbivores to expand their historical ranges.
DIVERSITY AND DISTRIBUTIONS
(2023)
Article
Ecology
Xin Zong, Tiejun Wang, Andrew K. Skidmore, Marco Heurich
Summary: This study demonstrates the use of three-dimensional cumulative viewshed in studying animal spatial behavior at a landscape level. The researchers utilized a combined terrestrial and airborne LiDAR technique to measure fine-scale habitat visibility in forested landscapes. The findings reveal the red deer's preference for intermediate habitat visibility and their adaptation of movement rate to fine-scale visibility. This research provides valuable insights into the influence of visibility on animal behavior and highlights the potential of LiDAR in animal ecology and behavior studies.
JOURNAL OF ANIMAL ECOLOGY
(2023)
Article
Geography, Physical
Simon Koenig, Frank Thonfeld, Michael Foerster, Olena Dubovyk, Marco Heurich
Summary: Bark beetle infestations are a significant forest disturbance agent that has been increasing in frequency and affected areas due to global climate change. This study demonstrates the potential of using multi-sensor time series data from Landsat and Sentinel satellites to detect and monitor bark beetle infestations, with Sentinel-2 providing the best overall results.
GISCIENCE & REMOTE SENSING
(2023)
Review
Ecology
Igor Khorozyan, Marco Heurich
Summary: The Eurasian lynx is an adaptable predator that takes ungulates according to their availability, rather than specializing in hunting hares. The predation on large prey is influenced by the density of prey populations and the forest environment. In the wild, ungulates, particularly roe deer, are the main food source for Eurasian lynx.
Article
Infectious Diseases
Janine Rietz, Suzanne T. S. van Beeck Calkoen, Nicolas Ferry, Jens Schlueter, Helena Wehner, Karl-Heinz Schindlatz, Tomas Lackner, Christian von Hoermann, Franz J. Conraths, Jorg Mueller, Marco Heurich
Summary: Because animal carcasses often serve as reservoirs for pathogens, their location and removal are crucial in controlling the spread of diseases. Recent studies have shown that infrared sensors can be used to locate animal carcasses, but little is known about the factors influencing detection success. In this study, we investigated the potential of infrared technology to locate wild boar carcasses, as they play an important role in the spread of African swine fever. Our results showed that the thermal camera accurately measured carcass temperature and that the probability of finding carcasses was influenced by environmental and carcass conditions such as habitat type, air temperature, canopy openness, and decomposition stage.
TRANSBOUNDARY AND EMERGING DISEASES
(2023)
Review
Ecology
Stefano Palmero, Joe Premier, Stephanie Kramer-Schadt, Pedro Monterroso, Marco Heurich
Summary: Robust monitoring is crucial for successful conservation planning, especially for elusive and low-density species like felids. This study examined the impact of sampling designs on the precision of population density estimates for territorial felids. Analysis of 137 camera-trapping and spatial capture-recapture studies revealed that the number of individuals captured, recapture frequency, and capture probability are the most important variables affecting precision. Guidelines for future studies and a reporting protocol were provided to improve the reproducibility and comparability of spatial capture-recapture research.
Article
Ecology
Hjalmar S. Kuehl, Stephen T. Buckland, Maik Henrich, Eric Howe, Marco Heurich
Summary: Among other approaches, camera trap distance sampling (CTDS) is used to estimate animal abundance from unmarked populations. This study introduces a new CTDS model for passive infrared motion sensor recording of single images or short photo series. By estimating mean time intervals, survey effort can be accurately calculated, avoiding underestimation of species abundance.
ECOLOGY AND EVOLUTION
(2023)
Article
Biodiversity Conservation
Igor Khorozyan, Marco Heurich
Summary: Human-carnivore conflicts over predation on domestic animals are a global challenge. Knowledge of determinants and patterns of predation on domestic animals is an essential prerequisite to develop and apply effective interventions against carnivores. We synthesized published information on Eurasian lynx (Lynx lynx) predation in terms of various factors and patterns of predation. The main domestic animals killed and consumed by lynx are semi-domestic reindeer and sheep. The predation patterns on these species are different, with reindeer being predated as a main wild prey species and sheep being killed upon chance encounters in predictable hotspot areas.
GLOBAL ECOLOGY AND CONSERVATION
(2023)
Article
Hospitality, Leisure, Sport & Tourism
Stefanie Doeringer, Florian Porst, Lena Stumpf, Marco Heurich
Summary: This study examined the effects of visitation numbers, perceived encounters, and expectations on perceived crowding in the Bavarian Forest National Park. The results showed that measured visitor density is a reliable indicator of perceived crowding, moderated by site-specific conditions. The calculated thresholds provide a valuable tool to inform the public about peak visiting times in advance.
Article
Biodiversity Conservation
Suzanne T. S. van Beeck Calkoen, Dries P. J. Kuijper, Marco Apollonio, Lena Blondel, Carsten F. Dormann, Ilse Storch, Marco Heurich
Summary: This study provides evidence for the dominant role played by humans (i.e. hunting, land-use activities) relative to large carnivores in reducing red deer density across European human-dominated landscapes. These findings suggest that when we would like large carnivores to exert numeric effects, we should focus on minimizing human impacts to allow the ecological impacts of large carnivores on ecosystem functioning.
JOURNAL OF APPLIED ECOLOGY
(2023)
Proceedings Paper
Geography, Physical
S. Dersch, A. Schoettl, P. Krzystek, M. Heurich
Summary: In this study, a novel tree detection method based on DETR is proposed for effectively detecting mixed and deciduous trees. DETR outperforms YOLOv4 by 28% and 5% in mixed and deciduous plots, respectively, but is inferior in coniferous plots.
XXIV ISPRS CONGRESS IMAGING TODAY, FORESEEING TOMORROW, COMMISSION II
(2022)
Article
Ecology
Marc Filla, Rinzin Phunjok Lama, Tim Filla, Marco Heurich, Niko Balkenhol, Matthias Waltert, Igor Khorozyan
Summary: This study aims to evaluate the effectiveness of various intervention strategies to protect snow leopards and livestock. The results suggest that the current main intervention strategies were not effective in reducing livestock losses, while the use of dogs, deterrents, and multiple interventions showed some potential. Controlled experiments should be conducted to further investigate and promote the most effective measures.
Article
Biodiversity Conservation
Tsegaye T. Gatiso, Lars Kulik, Mona Bachmann, Aletta Bonn, Lukas Boesch, Andreas Freytag, Marco Heurich, Karsten Wesche, Marten Winter, Isabel Ordaz-Nemeth, Tenekwetche Sop, Hjalmar S. Kuhl
Summary: Reconciling conservation and socioeconomic development goals is key to sustainability. A study found that protected areas play an essential role in achieving the synergies between biodiversity conservation and local socioeconomic development. Empowering PA management and involving local communities in planning and decision-making processes are crucial for the long-term sustainability of protected areas.