Multi-level multi-scale resource selection models using machine learning were compared and contrasted for generating predictive maps of jaguar habitat (Panthera onca) in the Brazilian Pantanal. Multiple spatial scales...Multi-level multi-scale resource selection models using machine learning were compared and contrasted for generating predictive maps of jaguar habitat (Panthera onca) in the Brazilian Pantanal. Multiple spatial scales and temporal movement levels were run within several analytical modeling frameworks for comparison. Included in the analysis were multi-scale raster grains (30 m, 90 m, 180 m, 360 m, 720 m, 1440 m) and GPS collaring temporal movement levels (point, path, and step). Various analytical methods were used for comparison of models that could accommodate data structural levels (group, individual, case-control). Models compared included conditional logistic regression, generalized additive modeling (GAM), and classification regression trees, such as random forests (RF) and gradient boosted regression tree (GBM). The goals of the study were to discuss the potential and limitations for machine learning methods using GPS collaring data to produce predictive habitat suitability mapping using the various scales and levels available. Results indicated that choosing the appropriate temporal level and raster scale improved model outputs. Overall, larger level analytical modeling frameworks and those that used multi-scale raster grains showed the best model evaluation with the inherent condition that they predict a broader scale and subset of data. The identification of the appropriate spatial scale, temporal scale and statistical model need careful consideration in predictive mapping efforts.展开更多
This study aims to identify the drivers of environmental degradation due to the dependency of surrounding residents on three protected areas in Togo, Africa (Oti-Keran, Togodo, and Abdoulaye national parks (abbr. OTA ...This study aims to identify the drivers of environmental degradation due to the dependency of surrounding residents on three protected areas in Togo, Africa (Oti-Keran, Togodo, and Abdoulaye national parks (abbr. OTA national parks)). Surveys of villagers conducted in and around the OTA national parks added to data downloaded from Indexmundi data portal. National-level trend analysis results indicated: 1) the number of terrestrial protected areas showed an upward trend, while savannah and forest cover showed alarming decrease trends. 2) At the local level, supplying socio-economic needs in the three selected protected areas directly resulted in biodiversity degradation through animal grazing, hunting and farming. 3) Over 70% of the respondent’s livelihoods consisted of farming and related dependencies on the protected areas for timber and non-timber forest products and income despite the protected status hold by these classified areas. 4) The OTA national parks have been experiencing an increase of anthropogenic pressure such as uncontrolled tree logging and hunting, which seriously impacts animal and vegetation biodiversity. 5) Policymakers should invest more resources in implementing an integrated management system based not only on a holistic vision of the PA that includes participatory management but also accounts for multi-dimensional principles to enable anthropogenic activities in and around the protected areas to satisfy sustainable development requirements.展开更多
During surveys for wild felids in Nangunhe Nature Reserve, Yunnan province, China, we conducted a wider mammal survey of the core nature reserve area, using camera trapping techniques. Forty motion-triggered digital c...During surveys for wild felids in Nangunhe Nature Reserve, Yunnan province, China, we conducted a wider mammal survey of the core nature reserve area, using camera trapping techniques. Forty motion-triggered digital camera traps had been set in oldest forest tract of protected area to conduct a species inventory. The total camera trapping effort of 2460 camera trap nights yielded 232 digital photographs of mammals represented by 17 species in ifve orders. The species photographed include rare and elusive species and those that are of high conservation value, such as IUCN endangered species Asiatic elephant （Elephas maximus）, and Phayre’s leaf monkey （Trachypit hecus phayrei）. In addition, IUCN vulnerable species including Asiatic black bear （Ursus thibetanus）, sambar （Rusa unicolor）, northern pig-tailed macaque （Macaca leonine）, and marbled cat （Pardofelis marmorata）, and more common species were found. Al mammals were also listed as key protected wild animals by the State Forestry Administration of China. Of particular importance were the carnivores, with 7 different species recorded. Ungulates and other taxa forming a prey base for these predators,such as rhesus macaque （Macaca mulatta）, red muntjac （Muntiacus muntjac）, sambar, wild boar （Sus scrofa）, and Chinese serow （Capricornis milneedwardsi）, were found to be the most frequently photographed and most widespread species. Opportunities for local people to develop standardized monitoring designs for targeted species were identiifed by these initial assessment results. Local nature reserve staff lacked technical ability to produce standardized survey designs, yet a by product of this type of non-standardized data collection can be very informative and produce inventory information that gives a species richness analysis, as well as initial estimates for occupancy and detection probability for abundant species to drive future standardized survey designs and efforts.展开更多
文摘Multi-level multi-scale resource selection models using machine learning were compared and contrasted for generating predictive maps of jaguar habitat (Panthera onca) in the Brazilian Pantanal. Multiple spatial scales and temporal movement levels were run within several analytical modeling frameworks for comparison. Included in the analysis were multi-scale raster grains (30 m, 90 m, 180 m, 360 m, 720 m, 1440 m) and GPS collaring temporal movement levels (point, path, and step). Various analytical methods were used for comparison of models that could accommodate data structural levels (group, individual, case-control). Models compared included conditional logistic regression, generalized additive modeling (GAM), and classification regression trees, such as random forests (RF) and gradient boosted regression tree (GBM). The goals of the study were to discuss the potential and limitations for machine learning methods using GPS collaring data to produce predictive habitat suitability mapping using the various scales and levels available. Results indicated that choosing the appropriate temporal level and raster scale improved model outputs. Overall, larger level analytical modeling frameworks and those that used multi-scale raster grains showed the best model evaluation with the inherent condition that they predict a broader scale and subset of data. The identification of the appropriate spatial scale, temporal scale and statistical model need careful consideration in predictive mapping efforts.
文摘This study aims to identify the drivers of environmental degradation due to the dependency of surrounding residents on three protected areas in Togo, Africa (Oti-Keran, Togodo, and Abdoulaye national parks (abbr. OTA national parks)). Surveys of villagers conducted in and around the OTA national parks added to data downloaded from Indexmundi data portal. National-level trend analysis results indicated: 1) the number of terrestrial protected areas showed an upward trend, while savannah and forest cover showed alarming decrease trends. 2) At the local level, supplying socio-economic needs in the three selected protected areas directly resulted in biodiversity degradation through animal grazing, hunting and farming. 3) Over 70% of the respondent’s livelihoods consisted of farming and related dependencies on the protected areas for timber and non-timber forest products and income despite the protected status hold by these classified areas. 4) The OTA national parks have been experiencing an increase of anthropogenic pressure such as uncontrolled tree logging and hunting, which seriously impacts animal and vegetation biodiversity. 5) Policymakers should invest more resources in implementing an integrated management system based not only on a holistic vision of the PA that includes participatory management but also accounts for multi-dimensional principles to enable anthropogenic activities in and around the protected areas to satisfy sustainable development requirements.
基金Second National Survey of Terrestrial Wildlife in China,State Forestry Administration of China
文摘During surveys for wild felids in Nangunhe Nature Reserve, Yunnan province, China, we conducted a wider mammal survey of the core nature reserve area, using camera trapping techniques. Forty motion-triggered digital camera traps had been set in oldest forest tract of protected area to conduct a species inventory. The total camera trapping effort of 2460 camera trap nights yielded 232 digital photographs of mammals represented by 17 species in ifve orders. The species photographed include rare and elusive species and those that are of high conservation value, such as IUCN endangered species Asiatic elephant （Elephas maximus）, and Phayre’s leaf monkey （Trachypit hecus phayrei）. In addition, IUCN vulnerable species including Asiatic black bear （Ursus thibetanus）, sambar （Rusa unicolor）, northern pig-tailed macaque （Macaca leonine）, and marbled cat （Pardofelis marmorata）, and more common species were found. Al mammals were also listed as key protected wild animals by the State Forestry Administration of China. Of particular importance were the carnivores, with 7 different species recorded. Ungulates and other taxa forming a prey base for these predators,such as rhesus macaque （Macaca mulatta）, red muntjac （Muntiacus muntjac）, sambar, wild boar （Sus scrofa）, and Chinese serow （Capricornis milneedwardsi）, were found to be the most frequently photographed and most widespread species. Opportunities for local people to develop standardized monitoring designs for targeted species were identiifed by these initial assessment results. Local nature reserve staff lacked technical ability to produce standardized survey designs, yet a by product of this type of non-standardized data collection can be very informative and produce inventory information that gives a species richness analysis, as well as initial estimates for occupancy and detection probability for abundant species to drive future standardized survey designs and efforts.
