Animal Molecular Breeding 2024, Vol.14, No.1, 130-140 http://animalscipublisher.com/index.php/amb 137 Another emerging technology is the application of reduced single nucleotide polymorphism (SNP) panels for genotyping degraded DNA samples, such as faeces or hairs. This approach allows for the efficient monitoring of wildlife populations, even with non-invasively collected samples, and can be tailored to address specific population genetics questions (Thaden et al., 2020). Furthermore, real-time telemetry and algorithm-based analytical capabilities are revolutionizing wildlife monitoring by enabling continuous tracking and analysis of animal movements and behaviors (Wall et al., 2014). These advancements facilitate more responsive and adaptive conservation strategies. 6.2 Role of artificial intelligence and machine learning Artificial Intelligence (AI) and Machine Learning (ML) are playing increasingly pivotal roles in wildlife monitoring and conservation. These technologies are being used to automate species identification, map and monitor habitats, and track population dynamics. For instance, machine learning algorithms have been developed to classify bird and amphibian calls, differentiate fish species, and identify plant species, making automated species identification possible (Drakshayini et al., 2023). The integration of AI with remote sensing techniques provides significant advantages for habitat mapping and monitoring, enabling more efficient and effective conservation strategies (Drakshayini et al., 2023). Deep learning, a subset of machine learning, has significantly advanced automatic wildlife recognition through camera trapping. However, current methods often rely on large static datasets, which can be limiting. A hybrid approach that combines machine learning with human input has been proposed to overcome these limitations, achieving high accuracy with reduced human annotation effort (Miao et al., 2021). This iterative human and automated identification approach enhances the efficiency and accuracy of wildlife monitoring. AI and ML are also being utilized in precision livestock farming, where sensing technologies supported by these algorithms monitor animal growth dynamics and activity status. Computer vision and wearable sensor systems are particularly effective in providing non-intrusive measurements of animals, accelerating phenotyping efforts and improving the quality of data collected (Morota et al., 2022). These advancements in AI and ML are transforming the field of wildlife monitoring, offering new tools and methodologies to support conservation efforts. In summary, the future of wildlife monitoring lies in the continued development and integration of emerging genomic technologies and AI-driven approaches. These innovations promise to enhance our ability to monitor, understand, and protect wildlife populations and their habitats. 7 Concluding Remarks The integration of genomics and remote sensing technologies has shown significant promise in advancing wildlife monitoring and conservation efforts. Genomics tools have provided precise estimates of critical population parameters such as effective population size, inbreeding, demographic history, and population structure, which are essential for conservation strategies. These tools have also enabled the identification of genetic loci responsible for inbreeding depression and adaptation to changing environments, thereby aiding in the management of adaptive variation. Remote sensing technologies, particularly when combined with machine learning, have revolutionized wildlife monitoring by automating species identification, mapping habitats, tracking population dynamics, and detecting wildlife crime. These technologies offer non-invasive methods to monitor and manage animal populations, providing significant advantages over traditional monitoring systems. Moreover, the application of genomics in marine environments has demonstrated the potential for rapid and cost-efficient monitoring, enhancing the assessment of marine health status and aiding in the implementation of marine legislation. The use of portable sequencing technologies in remote areas has also democratized scientific research, making it accessible to a broader network of conservation scientists. To further harness the potential of genomics and remote sensing technologies in wildlife monitoring, several steps need to be taken. First, there is a need for standardized guidelines and protocols to integrate these technologies into existing monitoring programs effectively. This includes developing comprehensive workflows for adaptive landscape genomics studies, which encompass sampling design, data production, and analysis. Second, addressing
RkJQdWJsaXNoZXIy MjQ4ODY0NQ==