A5075008796- Geographic Information Systems Studies
- Semantic Web and Ontologies
- Data Quality and Management
- Advanced Graph Neural Networks
- Data Management and Algorithms
- Multimodal Machine Learning Applications
- Coral and Marine Ecosystems Studies
- Island Studies and Pacific Affairs
- Mathematics, Computing, and Information Processing
- Robotics and Sensor-Based Localization
- Advanced Database Systems and Queries
- Smart Cities and Technologies
- Handwritten Text Recognition Techniques
- Green IT and Sustainability
- Recommender Systems and Techniques
- Disaster Management and Resilience
- Data Mining Algorithms and Applications
- Remote Sensing and LiDAR Applications
- Data Visualization and Analytics
- 3D Modeling in Geospatial Applications
- Underwater Acoustics Research
- Complex Network Analysis Techniques
- Marine and Coastal Ecosystems
- 3D Surveying and Cultural Heritage
- Diverse Aspects of Tourism Research
University of California, Santa Barbara
2014-2024
Sphere Institute
2019-2023
University of California System
2014
Abstract Knowledge graphs (KGs) are a novel paradigm for the representation, retrieval, and integration of data from highly heterogeneous sources. Within just few years, KGs their supporting technologies have become core component modern search engines, intelligent personal assistants, business intelligence, so on. Interestingly, despite large‐scale availability, they yet to be as successful in realm environmental intelligence. In this paper, we will explain why spatial require special...
The past decade has witnessed an increasing frequency and intensity of disasters, from extreme weather, drought, wildfires to hurricanes, floods, wars. Providing timely disaster response humanitarian aid these events is a critical topic for decision makers relief experts in order mitigate impacts save lives. When occurs, it important acquire first-hand, real-time information about the potentially affected area, its infrastructure, people develop situational awareness plan address health...
Knowledge graphs (KGs) are a novel paradigm for the representation, retrieval, and integration of data from highly heterogeneous sources. Within just few years, KGs their supporting technologies have become core component modern search engines, intelligent personal assistants, business intelligence, so on. Interestingly, despite large-scale availability, they yet to be as successful in realm environmental intelligence. In this paper, we will explain why spatial require special treatment, how...
Global challenges such as food supply chain disruptions, public health crises, and natural hazard responses require access to integration of diverse datasets, many which are geospatial. Over the past few years, a growing number (geo)portals have been developed address this need. However, most existing stacked by separated or sparsely connected data "silos" impeding effective consolidation. A new way sharing reusing geospatial is therefore urgently needed. In work, we introduce...
Abstract. Driven by foundation models, recent progress in AI and machine learning has reached unprecedented complexity. For instance, the GPT-3 language model consists of 175 billion parameters a training-data size 570 GB. While it achieved remarkable performance generating text that is difficult to distinguish from human-authored content, single training estimated produce over 550 metric tons CO2 emissions. Likewise, we see advances GeoAI research improving large-scale prediction tasks like...
A population of blue whales is resident off the southern coast Sri Lanka and has been observed year-round by crew a whalewatching vessel, Raja & Whales, few miles south Mirissa Harbour. Over course three years (1 December 2009 to 30 November 2012), total 485 whale sightings were reported with an average 4.56 individuals per sighting. This number does not represent seen because repeat highly probable. Calves during northeast monsoon. Sightings confined area about 200 n.miles that bisected...
Tourism is a significant driver of social and ecological change in developing countries, particularly small-island states, which are susceptible to tourism impacts due their particular environmental characteristics. In this article we present participatory mapping approach obtaining spatially explicit local perceptions future resulting from development, as well addressing the different community conflicts that may arise through introduction Solomon Islands community. The results show spatial...
Abstract. Generative AI based on foundation models provides a first glimpse into the world represented by machines trained vast amounts of multimodal data ingested these during training. If we consider resulting as knowledge bases in their own right, this may open up new avenues for understanding places through lens machines. In work, adopt thinking and select GPT-4, state-of-the-art representative family large language models, to study its geographic diversity regarding how well features...
A 1:2,000 scale orthophoto map of the southern coast Durai Island, Indonesia, was created using kite aerial photography and computer vision software. Photographs were taken a consumer-grade digital camera suspended from line that towed by boat along Durai's coastline. Three hundred fifty-seven photographs combined into mosaic, orthorectified georeferenced Agisoft PhotoScan software with ground control points collected via GPS field survey. The in conjunction underwater ecological surveys...
The coral reefs of Bali Barat National Park, one Indonesia’s oldest marine protected areas, are known for their high biodiversity and excellent sport diving; however, stressors such as destructive fishing practices, elevated water temperatures, damage from anchors careless visitors have been observed on these decades. purpose this study was to document quantify changes in the fish stony community structure within outside boundaries Park 2011 2016, including its most popular dive site,...
Generative AI based on foundation models provides a first glimpse into the world represented by machines trained vast amounts of multimodal data ingested these during training. If we consider resulting as knowledge bases in their own right, this may open up new avenues for understanding places through lens machines. In work, adopt thinking and select GPT-4, state-of-the-art representative family large language models, to study its geographic diversity regarding how well features are...
Geospatial Knowledge Graphs (GeoKGs) have become integral to the growing field of Artificial Intelligence. Initiatives like U.S. National Science Foundation's Open Network program aim create an ecosystem nation-scale, cross-disciplinary GeoKGs that provide AI-ready geospatial data aligned with FAIR principles. However, building this infrastructure presents key challenges, including 1) managing large volumes data, 2) computational complexity discovering topological relations via SPARQL, and...
Regional defaults describe the emerging phenomenon that text-to-image (T2I) foundation models used in generative AI are prone to over-proportionally depicting certain geographic regions exclusion of others. In this work, we introduce a scalable evaluation for uncovering such regional defaults. The consists region hierarchy--based image generation and cross-level similarity comparisons. We carry out an experiment by prompting DALL-E 2, state-of-the-art T2I model capable generating...
KnowWhereGraph is one of the largest fully publicly available geospatial knowledge graphs. It includes data from 30 layers on natural hazards (e.g., hurricanes, wildfires), climate variables air temperature, precipitation), soil properties, crop and land-cover types, demographics, human health, various place region identifiers, among other themes. These have been leveraged through graph by a variety applications to address challenges in food security agricultural supply chains;...
While the paths humans take play out in social as well physical space, measures to describe and compare their trajectories are carried abstract, typically Euclidean, space. When these applied of actual individuals an application area, alterations that inconsequential abstract space may suddenly become problematic once overlaid with geographic reality. In this work, we present a different view on trajectory similarity by introducing measure utilizes logical entailment. This is inferential...