Our proposal “Near Real-time Forecasting and Change Detection for an Open Ecosystem by Integrating Artificial Intelligence and Ecological Modeling” has been selected for an AI for Earth Microsoft Azure Compute Grant. We are awarded $15,000 computing credits for using Azure cloud services to develop and train geospatial deep learning models for biodiversity protection.
Open (i.e., non-forest) ecosystems, such as savannas, shrublands, and grasslands, make up over 40% of the global total ecosystem organic carbon, and harbor a substantial proportion of the world’s biodiversity. Accurately forecasting the state of vegetation and detecting abnormal changes are critical for managing the biodiversity, fire, water, and carbon in these open ecosystems. This proposed project will integrate state-of-the-art AI techniques with ecological models with the goal of providing accurate forecasting and change detection on the state of vegetation in an open ecosystem. We will focus on the Cape Floristic Region (CFR) of South Africa, which contains 20% of Africa’s plant diversity and is a Global Biodiversity Hotspot and UNESCO World Heritage Site. The outcomes of this project will include models and tools that can provide near real-time forecasting and change detection for the studied open ecosystem of CFR and could also be applied to other ecosystems with similar dynamics.
Our research team consists of:
• Dr. Yingjie Hu, Principal Investigator, GeoAI Lab, Department of Geography, University at Buffalo, State University of New York, United States
• Dr. Adam M. Wilson, Co-Investigator, Wilson Lab, Department of Geography, University at Buffalo, State University of New York, United States
• Dr. Glenn R. Moncrieff, Co-Investigator, Fynbos Node, South African Environmental Observation Network, South Africa
• Dr. Jasper A. Slingsby, Co-Investigator, Fynbos Node, South African Environmental Observation Network, South Africa
Our recent work on examining how people describe locations during natural disasters has been accepted as a full paper in the flagship GIScience conference. Due to COVID-19, this year’s conference is canceled; however, it is postponed to the next year, so it becomes GIScience 2021 🙂
Abstract: Social media platforms, such as Twitter, have been increasingly used by people during natural disasters to share information and request for help. Hurricane Harvey was a category 4 hurricane that devastated Houston, Texas, USA in August 2017 and caused catastrophic flooding in the Houston metropolitan area. Hurricane Harvey also witnessed the widespread use of social media by the general public in response to this major disaster, and geographic locations are key information pieces described in many of the social media messages. A geoparsing system, or a geoparser, can be utilized to automatically extract and locate the described locations, which can help first responders reach the people in need. While a number of geoparsers have already been developed, it is unclear how effective they are in recognizing and geo-locating the locations described by people during natural disasters. To fill this gap, this work seeks to understand how people describe locations during a natural disaster by analyzing a sample of tweets posted during Hurricane Harvey. We then identify the limitations of existing geoparsers in processing these tweets, and discuss possible approaches to overcoming these limitations.
Our lab member, Jimin Wang, recently completed his MS in GIS degree. His master project focuses on Advancing Spatial and Textual Analysis with GeoAI. Particularly, Jimin has published three related papers on this topic, which are:
Moving forward, Jimin has received a fellowship package from UB’s PhD Excellence Initiative which aims to “recruiting the very best PhD students and providing them with transformative academic programs that prepare them for future success”. Jimin will continue his study as a PhD student in our GeoAI Lab, and we look forward to his new achievements in the coming years.
Abstract: Social media messages, such as tweets, are frequently used by people during natural disasters to share real-time information and to report incidents. Within these messages, geographic locations are often described. Accurate recognition and geolocation of these locations is critical for reaching those in need. This paper focuses on the first part of this process, namely recognizing locations from social media messages. While general named entity recognition (NER) tools are often used to recognize locations, their performance is limited due to the various language irregularities associated with social media text, such as informal sentence structures, inconsistent letter cases, name abbreviations, and misspellings. We present NeuroTPR, which is a Neuro-net ToPonym Recognition model designed specifically with these linguistic irregularities in mind. Our approach extends a general bidirectional recurrent neural network model with a number of features designed to address the task of location recognition in social media messages. We also propose an automatic workflow for generating annotated datasets from Wikipedia articles for training toponym recognition models. We demonstrate NeuroTPR by applying it to three test datasets, including a Twitter dataset from Hurricane Harvey, and comparing its performance with those of six baseline models.
This paper is based on the panel discussion at the 2019 UCGIS Symposium on the Geospatial Humanities. We discussed the opportunities and challenges for conducting interdisciplinary research integrating GIScience and humanities as well as preparing students with necessary data analysis and visualization skills for geospatial humanities work. Very interesting panel discussion and a lot of research possibilities!
With the outbreak of COVID-19, we are deeply concerned about the safety and health of many GIScience students and scholars in Wuhan and in China. Along with UCSB STKO Lab and UW-Madison GeoDS Lab, we made this video to support Wuhan and China. Stay strong!
“The Austrian Academy of Sciences’ Commission for GIScience annually selects the winner of a ‘Young Researcher’ competition, based on an outstanding publication submitted by applicants enhancing the body of literature in Geoinformatics and GIScience.”
Geospatial artificial intelligence (GeoAI) is an interdisciplinary field that has received tremendous attention from both academia and industry in recent years. We recently published an article that reviews the series of GeoAI workshops held at the Association for Computing Machinery (ACM) International Conference on Advances in Geographic Information Systems (SIGSPATIAL) since 2017. These workshops have provided researchers a forum to present GeoAI advances covering a wide range of topics, such as geospatial image processing, transportation modeling, public health, and digital humanities. We provide a summary of these topics and the research articles presented at the 2017, 2018, and 2019 GeoAI workshops. We conclude with a list of open research directions for this rapidly advancing field.
Are We There Yet? Evaluating State-of-the-Art Neural Network based Geoparsers Using EUPEG as a Benchmarking Platform
Abstract: Geoparsing is an important task in geographic information retrieval. A geoparsing system, known as a geoparser, takes some texts as the input and outputs the recognized place mentions and their location coordinates. In June 2019, a geoparsing competition, Toponym Resolution in Scientific Papers, was held as one of the SemEval 2019 tasks. The winning teams developed neural network based geoparsers that achieved outstanding performances (over 90% precision, recall, and F1 score for toponym recognition). This exciting result brings the question “are we there yet?”, namely have we achieved high enough performances to possibly consider the problem of geoparsing as solved? One limitation of this competition is that the developed geoparsers were tested on only one dataset which has 45 research articles collected from the particular domain of Bio-medicine. It is known that the same geoparser can have very different performances on different datasets. Thus, this work performs a systematic evaluation of these state-of-the-art geoparsers using our recently developed benchmarking platform EUPEG that has eight annotated datasets, nine baseline geoparsers, and eight performance metrics. The evaluation result suggests that these
new geoparsers indeed improve the performances of geoparsing on multiple datasets although some challenges remain.
What is the current state-of-the-art in integrating results from artificial intelligence research into geographic information science and the earth sciences more broadly? Does GeoAI research contribute to the broader field of AI, or does it merely apply existing results? What are the historical roots of GeoAI? Are there core topics and maybe even moonshots that jointly drive this emerging community forward? We answer these questions in our recent editorial by providing an overview of past and present work, explain how a change in data culture is fueling the rapid growth of GeoAI work, and point to future research directions that may serve as common measures of success.