Deer-vehicle collisions (DVCs) along a 5.6-km segment of United States Highway 1 (US 1) on Big Pine Key (BPK), Florida responsible for approximately 26% of endangered Florida Key deer (Odocoileus virginianus clavium) annual mortalities. The Florida Department of Transportation (FDOT) constructed a 2.6-km long system of fencing, 2 underpasses, and 4 experimental deer guards to address DVCs along a portion of the US 1 roadway in 2001–2002. I evaluated the effectiveness of the project in reducing Key deer mortality by comparing (1) survival of radio-collared deer, (2) deer-vehicle collisions on US 1, and (3) determining the ability of deer to access the fenced segment. I found no significant difference in male or female survival. Key deer-vehicle collisions were reduced by 83–92% inside the fenced segment. However, overall US 1 Key deer-vehicle collisions did not change. Key deer entry into the fenced segment was minimized to 8 deer during the first-year resulting in 2 deer mortalities. I also assessed the potential impacts of the US 1 corridor project to Key deer movements by comparing (1) radio-collared Key deer annual ranges (2) radio-collared deer corridor movements, and (3) assessing Key deer underpass and corridor use. Female and male ranges and core areas did not change (P > 0.05). Deer movements within the US 1 corridor were comparable pre- (6 of 23 radio-collared deer crossed the corridor) and post-project (4 of 16). Infrared-triggered camera data indicate underpass movements increased over time. Collectively, post-project telemetry and camera data indicates US 1 highway improvements have not restricted Key deer movements. Hourly Key deer movement and US 1 traffic patterns were compared to annual US 1 DVCs. Hourly deer movements showed a positive correlation (P = 0.012, r = 0.505) to hourly DVCs for the full circadian period. Hourly US 1 traffic showed a significant positive relationship (P = 0.012, r = 0.787) with DVCs only during the night period. Evaluation of hourly deer movements and hourly traffic volume on US 1 found hourly DVCs to be the result of a combination between both variables.

The Department of Energy Oak Ridge Reservation (ORR) and the nearby adjoining City of Oak Ridge, Tennessee had experienced a rise in deer-vehicle collisions (DVCs) to the point where safety for employees and residents became a concern. I investigated the effect of hunting, land cover, road mileage, season, lunar phase, sex, and change in traffic patterns that coincide with work shifts on DVCs from 1975 - 2008. The study area was divided into grids of 1.5 km² each for administration and data recording by managing agencies. Statistical analyses were performed on the ORR (121 grids) and GIS analyses were performed on the entire study area that included ORR and the city of Oak Ridge (190 grids). The number of DVCs in 1975 was 16 and reached a high of 273 in 1985. Therefore, managers initiated a hunting program in 1985 and recorded deer harvest numbers by grid each year. Deer harvest has been occurring from 1985 until present, except when hunting was cancelled due to security concerns after the September 11 terrorist attacks in 2001. By 2008, the number of DVCs had decreased to 100 per year. When hunting first started in 1985, they harvested 926 deer. By 2008, that number was down to 481. I used GIS mapping to record DVCs, deer harvest per grid, landcover types, and mileage per grid to determine factors affecting DVCs on the smaller landscape. Following the initiation of annual hunts, both the annual deer harvest and the number of DVC’s have fallen, presumably because the overall deer population has declined from high pre-hunting levels. Deer harvest appears to be related to landcover characteristics, as a higher percentage of deer were harvested from forested areas than from other landcover types, as forested areas were most prominent. The months of October, November, and December had the highest DVC numbers. Increased traffic during starting and leaving shift times seem to increase the number of DVCs as well. Lunar phases only seem to significantly increase DVCs during the gestation and fawning seasons. Does are involved more frequently with DVCs than bucks during gestation, fawning and prerut, but not during the rutting season. I expect managers can use this data to guide intensive local management aimed at reducing DVCs by increasing the number of deer harvested and increased public education.

Road expansion and increased traffic likely exacerbates barriers to amphibian migration and dispersal. Within British Columbia’s south Okanagan valley there is particular concern that the COSEWIC-listed blotched tiger salamander (Ambystoma mavortium melanostictum) and Great Basin spadefoot (Spea intermontana) are vulnerable to road effects in their annual movements from upland overwintering habitat to lowland breeding areas. My study utilizes a before after control impact approach to assess amphibian movement and population threats across this highway-bisected landscape. Throughout the spring and summer of 2010-2012, fifty two kilometers of roadways (31 km of highway, 21 km of paved backroad) were repeatedly surveyed from the Canada-USA border to north of Oliver, BC; surveys were carried out utilising vehicles and on foot. Along Highway 97, a three kilometer four-lane highway expansion project was constructed through 2010 and open to traffic use in 2011. Adjacent to a floodplain, survey effort was focused throughout this transect for informed roadkill mitigation structure placement and ongoing ecopassage effectiveness monitoring. Automated camera trap monitoring of culverts within highly concentrated amphibian road hotspots during spring and summer 2011 (three culverts) and 2012 (two culverts) resulted in over eight hundred amphibian culvert events observed. Two sample Wilcoxon tests revealed differences between years in amphibian occurrence between 2010 and 2012 (W = 4679.5, p= 0.02), and mortalities among transect areas, with the largest differences between years within the Osoyoos passing lanes transect. Amphibian mortalities within the passing lanes transect were significantly reduced with the implementation of mitigation structures (x̅2010= 13.2 ± 32.5, x̅2011= 4.7 ± 12.8, x̅2012= 2.3 ± 7.3; 2010 vs. 2012: W= 1535.5, p< 0.001). Roadkill mitigation structures proved effective in observed amphibian occurrence of the entire passing lanes stretch as well as at distances 100 m and 200 m from observed culverts. Double fenced areas resulted in a 94% reduction in amphibian road occurrence. Five species of amphibians were observed over the three survey years (4051 road incidences over 657 survey hours): Pacific chorus frog (Pseudacris regilla), Western toad (Anaxyrus boreas), long-toed salamander (Ambystoma macrodactylum) plus blotched tiger salamander and Great Basin spadefoot. This study aims to provide a better understanding of amphibian hotspots on roadways and ecopassage use within the south Okanagan. It may act as a catalyst to further wildlife-vehicle interaction studies with improved mitigation solutions for amphibian roadway fatalities.

Roads can negatively impact the survival of wildlife populations through additional mortality from road kill and population fragmentation caused by road avoidance behaviors. The 11.9 mile section of State Route 101 between the towns of San Luis Obispo and Atascadero, CA, USA, cross a mountain lion movement corridor and an area important to maintaining ecological connectivity between protected lands in the Los Padres National Forest to the north and south. I examined the spatial patterns and landscape and roadway factors associated with road kill occurrence for six taxa; large mammals, mesocarnivores, squirrels, rabbits, birds and raptors. Between 1 May 2009 and 30 June 2010 road kills were documented using vehicle-based surveys. Small mammals were the most common road kill (58.3%), followed by mesocarnivores (10.9%), birds (10.6%), rabbits (5.1%), large mammals (3.3%) and raptors (3.2%). Twenty-nine large mammal road kills were observed during the survey period; eighteen mule deer, six black bears and five feral pigs. Road kill was highest in the middle of the survey area between the top of Cuesta Grade and the southern edge of Atascadero and lowest along the Cuesta Grade. I modeled road kill occurrence using logistic regression to determine which landscape and roadway characteristics were associated with road kill locations. Large mammal and mesocarnivore road kills were more likely to occur near riparian corridors. Mesocarnivore and squirrel road kills were associated with locations with greater roadside tree cover. Squirrel and rabbit road kills were more likely to occur along sections of the road with large grassy center medians. I documented animal activity patterns around the roadway during three survey periods (summer 2009, fall 2009 and spring 2010) using remote cameras placed on game trails and underpasses along the roadway. Mule deer displayed crepuscular activity patterns with peaks in activity in the morning between 05:00h and 07:00h and in the evening between 16:00h and 18:00h. Mesocarnivores generally displayed a nocturnal activity patterns with the majority of activity occurring between 18:00h and 06:00h. I used logistic regression to determine if there was a relationship between animal activity patterns and traffic patterns while controlling for time of day, day of the week, and season. Mule deer and mesocarnivore activity patterns varied significantly by time of day and mule deer activity also varied significantly by season; however only mesocarnivore activity varied significantly in relation to traffic volume suggesting that mesocarnivores are less activity when traffic volume is high. Using traffic volume and animal activity patterns I calculated a collision potential value for both mule deer and mesocarnivores. Collision potential for mule deer was high in the morning, between 06:00h and 08:00h, and in the evening, between 16:00h and 18:00h in all three seasons. Collision potential for mesocarnivores was high in the evening in fall 2009 (18:00h and 21:00) and spring 2010 (17:00h), and high in the morning in summer 2009 (09:00h).

The planned widening of U.S. Highway 17 along the east boundary of Great Dismal Swamp National Wildlife Refuge (GDSNWR) and a lack of knowledge about the refuge's bear population created the need to identify potential sites for wildlife crossings and estimate the size of the refuge's bear population. I collected black bear hair in order to collect DNA samples to estimate population size, density, and sex ratio, and determine road crossing locations for black bears (Ursus americanus) in GDSNWR in southeastern Virginia and northeastern North Carolina. I also investigated bear/vehicle collisions to determine patterns of road crossing. Genetic analysis of 344 hair samples collected on 2 trapping grids identified 85 unique individuals which I used in a mark-recapture analysis. Estimated population size on the trapping grids was 105 bears (95% CI = 91-148) and average density was 0.56 bears/km². This density estimate projected over the entire Great Dismal Swamp ecosystem yielded a population estimate of 308 bears (550 km2 X 0.56 bears/km²). Similar population estimates generated by Hellgren (1988), Tredick (2005), and this study suggest a stable bear population in the Great Dismal Swamp ecosystem over a 20-year period. I erected a 2.3-kilometer long strand of barbed wire along U. S. Highway 17 to monitor road crossing patterns near the Northwest River drainage. Genetic analysis identified 6 bears (4 males, 1 female, 1 unknown) that apparently crossed the highway in a 10-month period. Five of 6 bears deposited hair in a 171-m section which included the Northwest River corridor. The 6 bears detected crossed the road at least 11 times. I investigated 10 reports of bear/vehicle collisions on the periphery of the refuge from June 2000 to May 2002. Six bears (4M:1F:1 unknown) were confirmed killed during this time period. Based on reported bear/vehicle collisions from Hellgren (1988), the Virginia Department of Game and Inland Fisheries database, and this study, a minimum of 4 to 5 bears are struck by vehicles each year on the periphery of the refuge. I identified 2 areas of multiple bear/vehicle collisions: highway 58 on the north side of the refuge near Hampton Airport and Highway 17 on the eastern side of the refuge in the vicinity of the Northwest River corridor. / Master of Science

Deer Vehicle Collisions (DVCs) are a global problem that is not only resulting in seriousinjuries to humans but also results in loss of human and deer lives. Deer are more active and less attentive during the mating and hunting seasons. Roadside deer activity such as feeding and strolling along the roadside has a significant correlation with DVCs. To mitigate DVCs, several strategies were used that include vegetation management, fences, underpasses and overpasses, population reduction, warning signs and animal detection systems (ADS). These strategies vary in their efficacy. These strategies may help to reduce DVCs. However, they are not always easily feasible due to false alarms, high cost, unsuitable terrain, land ownership, and other factors. Thus, DVCs are increasing due to the increase in number of vehicles and the absence of intelligent highway safety and alert systems. Detecting deer in real-time on our roads is a challenging problem. Thus, this research work proposed a deer detection and movement DDM technique to automate DVCs mitigation system. The DDM combines computer vision, artificial intelligent methods with deep learning techniques. DDM includes two main deep learning algorithms 1)onestage deep learning algorithm based on Yolov5 that generates a detection model(DM) to detect deer and 2) deep learning algorithm developed by python toolkit DeepLabCut to generate movement model(MM) for detecting the movement of the deer. The proposed method can detect deer with 99.7% precision and succeeds to ascertain if the deer is moving or static with an inference speed of 0.29s. The proposed method can detect deer with 99.7% precision and using DeepLabCut toolkit on the detected deer we can ascertain if the deer is moving or static with an inference speed of 0.29s.

Rerouting highways to accommodate construction of the Jordanelle Reservoir in northeastern Utah caused a dramatic increase in vehicle collisions with mule deer (Odocoileus hemionus). I evaluated the effectiveness of a new system of highway crosswalk structures installed to reduce deer losses and preserve seasonal migrations. In addition, I constructed computer simulation models to investigate how highway mortality has impacted the Jordanelle deer population. The crosswalk system restricted deer crossings to specific, well-marked areas along highways where motorists could anticipate them. Subsequent to installation, mortality declined 42.3% and 36.8% along a four-lane and two-lane highway, respectively. I was unable to statistically demonstrate that observed mortality reductions were a direct result of the crosswalk system. The potential applicability of the structures, however, should not be dismissed. Reduced deer use of the highway right-of-way (ROW), the apparent maintenance of migratory behavior, and observations of animals crossing within crosswalk boundaries indicate the system warrants further testing. Lack of motorist response to crosswalk warning signs, the tendency for foraging deer to wander outside crosswalk boundaries, and the ineffectiveness of ROW escape gates contributed to most treatment area mortalities. I offer design modifications that address these shortcomings. Four years of field data revealed that highway mortality at Jordanelle was inversely density-dependent, removed between 5.6% and 17.4% of the population each year, and disproportionately impacted bucks. I incorporated this information into 3 competing simulation models in which highway losses operated in a strictly additive, partially compensatory, or strictly compensatory manner. The partial compensation model most closely tracked observed population dynamics, suggesting that highway losses were not completely offset by reductions in other mortality sources. Highway mortality apparently worsened a population crash initiated by severe winter conditions, and may be slowing the recovery. The disproportionate loss of bucks along roads altered sex ratios of simulated populations. Mitigative efforts should target road-kill reductions >60% to avoid population declines predicted by the partial compensation model. Annual variation in demographic parameters offset the impacts of highway mortality at high population levels. At low population levels, however, highway mortality was severe enough to drive declining population trends.

Ambulanssjuksköterskan ska i sin profession kunna bedöma, vårda och transportera på ett korrekt och patientsäkert sätt in till sjukhus. Den prehospitalt specialiserade sjuksköterskanförväntas bemästra en rad uppgifter vilket inkluderar en ökad säkerhetsmedvetenhet både för sig själv och för sin patient. En ambulans skiljer sig från övriga utryckningsfordon i trafiken då den förväntas klara av att transportera akut sjuka patienter med avancerat omvårdnadsbehov, dagens ambulansfordon är större i storlek och innehåller mer medicinskteknisk utrustning än sina föregångare. Vårdutrymmet är ambulanssjuksköterskans huvudsakliga arbetsmiljö som ibland delas med extra specialistpersonal eller närstående till patienten. I tidigare studier har ambulanspersonalens egna tankar och upplevelser inte beskrivits i någon större utsträckning, utan fokus har legat på i vilken omfattning ambulansrelaterade skadehändelser skett i trafiken och vilka yttre omständigheter som figurerat samt vårdutrymmets utformning. Syftet med studien var att belysa ambulanssjuksköterskans upplevelser av patientsäkerhet vid omvårdnadsåtgärder under patienttransport. Metoden som användes var en intervjustudie med deskriptiv design. Datainsamling skedde genom sju semistrukturerade intervjuer från verksamma ambulanssjuksköterskor i Mellansverige. Intervjuerna analyserades därefter enligt en manifest innehållsanalys. Fyra huvudkategorier framkom i resultatet; begränsande och hindrande vårdutrymme, preventiva transportåtgärder, riskfylld och risktagande omvårdnad samt hinder i lastsäkring. Utformningen av vårdutrymmet visade sig från vårdarstolen sett begränsa åtkomst till både patient och utrustning samt att vissa åtgärder var omöjliga att genomföra med bilbälte på. Preventiva transportåtgärder i den mån det var möjligt samt samverkan inom ambulansbesättningen och med övriga medföljande ansågs allmänt öka säkerheten ombord. En form av risktagande omvårdnad bedrevs om patientens status var instabil eller kritisk; återkommande exempel av detta var vid illamående patienter eller vid hjärt- och lungräddning under transport. Samtliga ambulanssjuksköterskor var eniga om att just dessa situationer medförde obältat arbete. Avsaknad av adekvat lastsäkring av utrustning medförde improviserade förankringar och ibland lösa föremål. Flertalet ambulanssjuksköterskor angav att intensivvårdstransporter var särskilt oroande. Slutligen underströks även att delar av ambulansens befintliga utrustning inte var anpassade efter patienter med avvikande små eller stora kroppsstorlekar vilket medförde inadekvat fixering och förankring. Slutsatsen var att patientsäkerhet under transport utgick från vårdutrymmets utformning samt ambulanssjuksköterskans fysiska förmåga att utföra ergonomiska såväl som obekväma uppgifter. Vidare var arbetslivserfarenhet och kompetens av vikt för att interventioner skulle vara möjliga och att de genomfördes vid rätt tidpunkt. Klinisk erfarenhet och kompetensnivå var en förutsättning för säker vård och essentiellt för det prehospitala utvecklingsarbetet. Ambulansens utrustning var i flera avseenden inte modulär och genom den bristande graden av anpassningsbarhet förekom ett kalkylerande risktagande hos den prehospitala personalen. Genom ett självuppoffrande beteende hos ambulanssjuksköterskan ansågs vårdkvalitén öka i vissa avseenden samtidigt minska i andra. Det övergripande synsättet som beskrevs var en inställning att lösa prehospitala utmaningar med till hands tillgängliga medel och utifrån det altruistiska synsättet att sätta patienten i första rum. / The ambulance nurses must in their professional role know how to asses, treat and transport patients in a correct and safe manner to the hospital. The prehospital specialist nurse is expected to master several tasks which include an increased safety awareness both for themselves and for their patient. An ambulance differs from other emergency vehicles in traffic as it is expected to be capable of transporting acutely sick or ill patient in need of advanced medical care. Today's ambulance vehicles are larger in size and contain more medical equipment than their predecessors. The care space is the ambulance nurses´ main workplace which sometimes is shared with additional specialist staff or related kin to the patient. In previous studies the ambulance staff's own thoughts and experiences are not described in any great extent, the focus has been towards ambulance-related injury events occurred in traffic and what external factors that were present. The aim was to illustrate the ambulance nurses´ experiences of nursing interventions in the ambulance care space during patient transport. The method used was an interview study with a descriptive design. Data collection took place through seven semi-structured interviews from ambulance nurses in central Sweden. The interviews were then analyzed according to a manifest content analysis. Four main categories emerged in the result; restrictive and preventive care space, preventative transport measures, risky and risk-taking care and barriers to securing cargo.The design of the ambulance care space showed that the provider seat limited access to patient and equipment and that certain procedures were impossible to carry out while wearing seatbelt. Preventative transport measures, cooperation within the ambulance crew and that with others accompanying were considered to increase the general safety onboard. A form of risk-taking care was undertaken if the patient’s status was unstable or critical; a recurrent example of this were in nauseated patients or during cardiopulmonary resuscitation while in transport. All ambulance nurses agreed that these situations inparticular led to managing the patient while unbelted. The lack of adequate cargo securing methods resulted in improvised anchoring and sometimes loose objects in the ambulancecare space. Particularly worrying was the intensive care transports according to themajority of the ambulance nurses. It was also emphasized that part of the ambulance’s existing equipment was not adapted to patients with divergent small or large body sizes which resulted in inadequate fixation and anchoring. The conclusion was that patient safety emanated from the care space design and the ambulance nurse's physical ability to perform ergonomic as well as uncomfortable tasks during transport. Furthermore, work experience and competence were important for interventions to be possible and that they were implemented at the right time. Clinical experience and skill level were a prerequisite for safe care and essential for prehospital development work. The ambulance equipment was in many respects not modular and, due to the lack of degree of adaptability, there was a calculating risk-taking behavior by the prehospital staff. Through a self-sacrificing behavior of the ambulance nurse, the care quality was considered to increase in some respects while decreasing in others. The overall approach described was that prehospital challenges was to be solved with whatever means available and on the basis of the altruistic approach to put patients’ needs first.

A construção e ampliação de rodovias gera impactos significativos ao meio ambiente. Os principais impactos ao meio biótico são a supressão de vegetação, redução da riqueza e abundância de espécies de fauna como decorrência da fragmentação de habitats e aumento dos riscos de atropelamento de animais silvestres e domésticos. O objetivo geral do trabalho foi identificar padrões espaciais nos atropelamentos de fauna silvestre por espécie (nome popular) utilizando ferramentas de análise espacial e machine learning. Especificamente, buscou-se compreender a relação entre atropelamentos de animais silvestres e variáveis que representam características de uso e cobertura do solo e caracterização da rodovia, tais como formação florestal, corpos d\'água, silvicultura, áreas edificadas, velocidade máxima permitida, volume de tráfego, entre outras. Os atropelamentos de fauna silvestre foram analisados por espécie atropelada, a fim de identificar os padrões espaciais dos atropelamentos específicos para cada espécie. As ferramentas de análise espacial empregadas foram a Função K - para determinar o padrão de distribuição dos registros de atropelamento de fauna, o Estimador de Densidade de Kernel - para gerar estimativas de densidade de pontos sobre a rodovia, a Análise de Hotspots - para identificar os trechos mais críticos de atropelamento de fauna e, por fim, o Self-Organizing Maps (SOM), um tipo de rede neural artificial, que reorganiza amostras de dados n-dimensionais de acordo com a similaridade entre elas. Os resultados das análises de padrões pontuais foram importantes para entender que os pontos de atropelamento possuem padrões de distribuição espacial que variam por espécie. Os eventos ocorrem espacialmente agrupados e não estão homogeneamente distribuídos ao longo da rodovia. De maneira geral, os animais apresentam trechos de maior intensidade de atropelamento em locais distintos. O SOM permitiu analisar as relações entre múltiplas variáveis, lineares e não-lineares, tais como são os dados ecológicos, e encontrar padrões espaciais distintos por espécie. A maior parte dos animais foi atropelada próxima de fragmentos florestais e de corpos d\'água, e distante de cultivo de cana-de-açúcar, silvicultura e área edificada. Porém, uma parte considerável das mortes de animais dos tipos com maior número de atropelamentos ocorreu em áreas com paisagem diversificada, incluindo alta densidade de drenagem, fragmentos florestais, silvicultura e áreas edificadas. / The construction and expansion of roads cause significant impacts on the environment. The main potential impacts to biotic environment are vegetation suppression, reduction of the abundance and richness of species due to forest fragmentation and increase of animal (domestic and wildlife) vehicle collisions. The general objective of this work was to identify spatial patterns in wildlife-vehicle collisions individually per species by using spatial analysis and machine learning. Specifically, the relationship between wildlife-vehicle collisions and variables that represent land use and road characterization features - such as forests, water bodies, silviculture, sugarcane fields, built environment, speed limit and traffic volume - was investigated. The wildlife-vehicle collisions were analyzed per species, in order to identify the spatial patterns for each species separately. The spatial analysis tools used in this study were K-Function - to determine the distribution pattern of roadkill, Kernel Density Estimator (KDE) - to identify the location and intensity of hotspots and hotzones. Self-Organizing Maps (SOM), an artificial neural network (ANN), was selected to reorganize the multi-dimensional data according to the similarity between them. The results of the spatial pattern analysis were important to perceive that the point data pattern varies between species. The events occur spatially clustered and are not uniformly distributed along the highway. In general, wildlife-vehicle collsions have their hotzones in different locations. SOM was able to analyze the relationship between multiple variables, linear and non-linear, such as ecological data, and established distinct spatial patterns per each species. Most of the wildlife was run over close to forest area and water bodies, and distant from sugarcane, silviculture and built environments. But a considerable part of the wildlife-vehicle collisions occurred in areas with diverse landscape, including high density of water bodies, silviculture and built environments.

A construção e ampliação de rodovias gera impactos significativos ao meio ambiente. Os principais impactos ao meio biótico são a supressão de vegetação, redução da riqueza e abundância de espécies de fauna como decorrência da fragmentação de habitats e aumento dos riscos de atropelamento de animais silvestres e domésticos. O objetivo geral do trabalho foi identificar padrões espaciais nos atropelamentos de fauna silvestre por espécie (nome popular) utilizando ferramentas de análise espacial e machine learning. Especificamente, buscou-se compreender a relação entre atropelamentos de animais silvestres e variáveis que representam características de uso e cobertura do solo e caracterização da rodovia, tais como formação florestal, corpos d\'água, silvicultura, áreas edificadas, velocidade máxima permitida, volume de tráfego, entre outras. Os atropelamentos de fauna silvestre foram analisados por espécie atropelada, a fim de identificar os padrões espaciais dos atropelamentos específicos para cada espécie. As ferramentas de análise espacial empregadas foram a Função K - para determinar o padrão de distribuição dos registros de atropelamento de fauna, o Estimador de Densidade de Kernel - para gerar estimativas de densidade de pontos sobre a rodovia, a Análise de Hotspots - para identificar os trechos mais críticos de atropelamento de fauna e, por fim, o Self-Organizing Maps (SOM), um tipo de rede neural artificial, que reorganiza amostras de dados n-dimensionais de acordo com a similaridade entre elas. Os resultados das análises de padrões pontuais foram importantes para entender que os pontos de atropelamento possuem padrões de distribuição espacial que variam por espécie. Os eventos ocorrem espacialmente agrupados e não estão homogeneamente distribuídos ao longo da rodovia. De maneira geral, os animais apresentam trechos de maior intensidade de atropelamento em locais distintos. O SOM permitiu analisar as relações entre múltiplas variáveis, lineares e não-lineares, tais como são os dados ecológicos, e encontrar padrões espaciais distintos por espécie. A maior parte dos animais foi atropelada próxima de fragmentos florestais e de corpos d\'água, e distante de cultivo de cana-de-açúcar, silvicultura e área edificada. Porém, uma parte considerável das mortes de animais dos tipos com maior número de atropelamentos ocorreu em áreas com paisagem diversificada, incluindo alta densidade de drenagem, fragmentos florestais, silvicultura e áreas edificadas. / The construction and expansion of roads cause significant impacts on the environment. The main potential impacts to biotic environment are vegetation suppression, reduction of the abundance and richness of species due to forest fragmentation and increase of animal (domestic and wildlife) vehicle collisions. The general objective of this work was to identify spatial patterns in wildlife-vehicle collisions individually per species by using spatial analysis and machine learning. Specifically, the relationship between wildlife-vehicle collisions and variables that represent land use and road characterization features - such as forests, water bodies, silviculture, sugarcane fields, built environment, speed limit and traffic volume - was investigated. The wildlife-vehicle collisions were analyzed per species, in order to identify the spatial patterns for each species separately. The spatial analysis tools used in this study were K-Function - to determine the distribution pattern of roadkill, Kernel Density Estimator (KDE) - to identify the location and intensity of hotspots and hotzones. Self-Organizing Maps (SOM), an artificial neural network (ANN), was selected to reorganize the multi-dimensional data according to the similarity between them. The results of the spatial pattern analysis were important to perceive that the point data pattern varies between species. The events occur spatially clustered and are not uniformly distributed along the highway. In general, wildlife-vehicle collsions have their hotzones in different locations. SOM was able to analyze the relationship between multiple variables, linear and non-linear, such as ecological data, and established distinct spatial patterns per each species. Most of the wildlife was run over close to forest area and water bodies, and distant from sugarcane, silviculture and built environments. But a considerable part of the wildlife-vehicle collisions occurred in areas with diverse landscape, including high density of water bodies, silviculture and built environments.