Thumbnail Image

SMART Global Ecosystems an academic-industrial partnership to integrate artificial intelligence in forestry

XV World Forestry Congress, 2-6 May 2022









Also available in:
No results found.

Related items

Showing items related by metadata.

  • Thumbnail Image
    Article
    Mapping street trees using google street view and artificial intelligence.
    XV World Forestry Congress, 2-6 May 2022
    2022
    Also available in:
    No results found.

    Urban forests provide ecosystem services to the increasingly urban society, contributing to human wellbeing in cities. While individual-tree characterization and identification are crucial for an efficient and accurate evaluation of urban biodiversity and ecosystem services, the available information on urban trees is rather limited worldwide. Currently, forest inventories require a large amount of human and economic resources, which limit their applicability. Some open data sources such as Google Street View (GSV) offer ground-level images in most urban areas around the world, which, coupled with computer vision techniques and artificial intelligence, provide a promising alternative to fieldwork to conduct urban forest inventories with the aim of characterizing tree diversity and structure and related ecosystem services. Our research aimed at using open data sources such as GSV to map and inventory street trees through an artificial intelligence engine. We developed an automatic transfer learning-based method that allows us to identify urban trees in the images, and the use of remote sensing techniques for geopositioning validation to properly map them with high accuracy (>75%). This method was validated with GSV and Google Maps images as well as with the ground-sourced forest inventory in an urban area (city of Lleida, Spain). This research highlights the potential of artificial intelligence in forest science to generate accurate and efficient mapping of trees, particularly in urban forest ecosystems. Keywords: Innovation, Adaptive and integrated management, Human health and well-being, Monitoring and data collection, Landscape management ID: 3482699
  • Thumbnail Image
    Document
    Growth estimation of standing trees using artificial intelligence
    XV World Forestry Congress, 2-6 May 2022
    2022
    Also available in:
    No results found.

    Growth assessment in an ecosystem is an essential element in management and decision making. Such an exercise helps in development and biodiversity management in a natural ecosystem. The assessment process, however, demands time and manpower. Developing an automated tool not only helps in saving the above-mentioned resources but also in expanding the area of coverage for assessment. We are developing an artificial intelligence based tool using image data for growth assessment. The method will be demonstrated in plantations of eucalyptus and teak. The plantations are established in straight lines using a single species of trees. It can be assumed that the trunk texture of these trees is similar while the shape can be different. Estimating the standing timber volume is important to assess the growth, harvestable timber volume, and plan on the transportation logistics of harvested timber. Every tree must be manually measured in the existing method of volume calculation demanding time and manpower. These costs can be cut down while maintaining the accuracy using images processed with statistical learning methods such as Convolutional Neural Network. The plantations will be partitioned into grids and digital images will be taken from the edges of this grid. These RGB digital images will be processed to determine the growth parameters such as girth at breast height, height, and tapering of the trees. Transfer Learning is to be used in modifying the existing neural network in identifying 3D shapes of individual objects from 2D images, multi-spatial depth estimation, and volume determination. A cost-effective automated tool to estimate the timber volume of standing trees in real-time will be developed. While estimating the volume by this method, a significant amount of time and manpower can be saved without compromising the accuracy compared to the conventional method. Keywords: Monitoring and data collection, Adaptive and integrated management, Innovation, Policies, Research ID: 3621691
  • Thumbnail Image
    Article
    Forestry education in Nigeria: Are forestry students unwilling to study the course and does it influence their academic performance?
    XV World Forestry Congress, 2-6 May 2022
    2022
    Also available in:
    No results found.

    Forestry education in Nigeria, as it is globally, is faced with several drawbacks despite the urgent need to train more professionals who can tackle the increasing issues related to forestry. One of these concerns is the reducing interest in academic forestry programs evident by low enrolment rates. However, forestry education still pools relatively good enrolment across Nigerian tertiary institutions, often due to candidates’ inability to secure their initially desired courses. Meanwhile, this could have influenced their academic achievements and career progressions. This study, therefore, analysed the unwillingness of forestry students in Nigeria to study the course and its impact on their academic performance, taking the department of Forestry at FUTA as a case study. A survey was used to collect data from the students (193) on four study levels, comprising their demographics, unwillingness to study forestry, interest to further in forestry-related works and studies, and their academic performance. Descriptive and Chi-square statistics were then used to analyse the responses. The results show that majority of the students were male (56%), mainly within the ages 20-25 (60%) and had been admitted via the Unified Tertiary Matriculation Examination (63%) with no prior forestry awareness, unlike the direct-entry students who mostly had post-secondary forestry-related experience. Widely, students’ perception evidenced their unwillingness towards the discipline with about 68%, 65%, and 94% of them not having prior knowledge about forestry before admission, never chose the course, and would not wish to further in any related post-study engagements, respectively. Meanwhile, only their educational background and their parents' educational level were found to have influenced their unwillingness. It was also revealed that this unwillingness impacted their academic performance significantly. Therefore, Forestry education should be made more attractive in every way possible to facilitate students’ interest and consequently improve academic performance and professional competence in forestry sector. Keywords: Forestry education, unwillingness, interest, influence and academic performance ID: 3623841

Users also downloaded

Showing related downloaded files

No results found.