An official website of the United States government
Environmental conservation organizations routinely monitor news content on conservation in protected areas to maintain situational awareness of developments that can have an environmental impact. Existing automated media monitoring systems require large amounts of data labeled by domain experts, which is only feasible at scale for high-resource languages like English. However, such tools are most needed in the global south where the news of interest is mainly in local low-resource languages, and far fewer experts are available to annotate datasets on a sustainable basis. In this paper, we propose NewsSerow, a method to automatically recognize environmental conservation content in low-resource languages. NewsSerow is a pipeline of summarization, in-context few-shot classification, and self-reflection using large language models (LLMs). Using at most 10 demonstration example news articles in Nepali, NewsSerow significantly outperforms other few-shot methods and can achieve comparable performance with models fully fine-tuned using thousands of examples. With NewsSerow, Organization X has been able to deploy the media monitoring tool in Nepal, significantly reducing their operational burden, and ensuring that AI tools for conservation actually reach the communities that need them the most. NewsSerow has also been deployed for countries with other languages like Colombia.
more »
« less
NewsPanda: Media Monitoring for Timely Conservation Action
Non-governmental organizations for environmental conservation have a significant interest in monitoring conservation-related media and getting timely updates about infrastructure construction projects as they may cause massive impact to key conservation areas. Such monitoring, however, is difficult and time-consuming. We introduce NewsPanda, a toolkit which automatically detects and analyzes online articles related to environmental conservation and infrastructure construction. We fine-tune a BERT-based model using active learning methods and noise correction algorithms to identify articles that are relevant to conservation and infrastructure construction. For the identified articles, we perform further analysis, extracting keywords and finding potentially related sources. NewsPanda has been successfully deployed by the World Wide Fund for Nature teams in the UK, India, and Nepal since February 2022. It currently monitors over 80,000 websites and 1,074 conservation sites across India and Nepal, saving more than 30 hours of human efforts weekly. We have now scaled it up to cover 60,000 conservation sites globally.
more »
« less
- Award ID(s):
- 2046640
- PAR ID:
- 10490460
- Publisher / Repository:
- AAAI
- Date Published:
- Journal Name:
- Proceedings of the AAAI Conference on Artificial Intelligence
- Volume:
- 37
- Issue:
- 13
- ISSN:
- 2159-5399
- Page Range / eLocation ID:
- 15528 to 15536
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Amid a global infrastructure boom, there is increasing recognition of the ecological impacts of the extraction and consumption of construction minerals, mainly processed as concrete, including significant and expanding threats to global biodiversity. We investigated how high‐level national and international biodiversity conservation policies address mining threats, with a special focus on construction minerals. We conducted a review and quantified the degree to which threats from mining these minerals are addressed in biodiversity goals and targets under the 2011–2020 and post‐2020 biodiversity strategies, national biodiversity strategies and action plans, and the assessments of the Intergovernmental Science–Policy Platform on Biodiversity and Ecosystem Services. Mining appeared rarely in national targets but more frequently in national strategies. Yet, in most countries, it was superficially addressed. Coverage of aggregates mining was greater than coverage of limestone mining. We outline 8 key components, tailored for a wide range of actors, to effectively mainstream biodiversity conservation into the extractive, infrastructure, and construction sectors. Actions include improving reporting and monitoring systems, enhancing the evidence base around mining impacts on biodiversity, and modifying the behavior of financial agents and businesses. Implementing these measures could pave the way for a more sustainable approach to construction mineral use and safeguard biodiversity.more » « less
-
null (Ed.)Abstract In India, high rates of antibiotic consumption and poor sanitation infrastructure combine to pose a significant risk to the public through the environmental transmission of antimicrobial resistance (AMR). The WHO has declared extended-spectrum beta-lactamase (ESBL)-positive Escherichia coli a key indicator for the surveillance of AMR worldwide. In the current study, we measured the prevalence of AMR bacteria in an urban aquatic environment in India by detecting metabolically active ESBL-positive E. coli. Water samples were collected in duplicate from 16 representative environmental water sources including open canals, drains, and rivers around Kanpur, Uttar Pradesh. We detected culturable E. coli in environmental water at 11 (69%) of the sites. Out of the 11 sites that were positive for culturable E. coli, ESBL-producing E. coli was observed at 7 (64%). The prevalence of ESBL-producing E. coli detected in the urban aquatic environment suggests a threat of AMR bacteria to this region.more » « less
-
Abstract Understanding species distributions is a global priority for mitigating environmental pressures from human activities. Ample studies have identified key environmental (climate and habitat) predictors and the spatial scales at which they influence species distributions. However, regarding human influence, such understandings are largely lacking. Here, to advance knowledge concerning human influence on species distributions, we systematically reviewed species distribution modelling (SDM) articles and assessed current modelling efforts. We searched 12,854 articles and found only 1,429 articles using human predictors within SDMs. Collectively, these studies of >58,000 species used 2,307 unique human predictors, suggesting that in contrast to environmental predictors, there is no ‘rule of thumb’ for human predictor selection in SDMs. The number of human predictors used across studies also varied (usually one to four per study). Moreover, nearly half the articles projecting to future climates held human predictors constant over time, risking false optimism about the effects of human activities compared with climate change. Advances in using human predictors in SDMs are paramount for accurately informing and advancing policy, conservation, management and ecology. We show considerable gaps in including human predictors to understand current and future species distributions in the Anthropocene, opening opportunities for new inquiries. We pose 15 questions to advance ecological theory, methods and real-world applications.more » « less
-
The Indian summer monsoon (ISM), which today supplies ~75% of annual precipitation to South Asia, has been reconstructed across previous centuries using a variety of hydroclimate-sensitive proxies. In some of these cases, ISM variability far exceeds that observed in the century-and-a-half-long instrumental record. Understanding the origins of these events is best addressed by developing a wide-ranging, multi-proxy network of high-resolution ISM reconstructions. In Nepal, ISM variability has been examined through tree rings, glacial ice, and lake sediments, but no stalagmite isotopic records of ISM rainfall have yet been published. Here we present a sub-decadally-resolved, precisely-dated, composite aragonite stalagmite record of ISM variability from Siddha Baba cave, central Nepal, for the last 2.7 kyr. A rainwater sampling program near the cave site, and a published study from Kathmandu (Adhikari et al., 2020), 150 km to the southeast, reveal that rainfall amount explains little of the observed variance in d18O values. Local hydroclimate is thus reconstructed from stalagmite 13C values, which we interpret as reflecting prior aragonite precipitation driven by changes in effective precipitation above the cave. ISM variability is apparent across a number of time scales, including centennial periods of reduced or enhanced rainfall coincident with societally-relevant precipitation regimes identified at other sites across South Asia. These include the Neo-Assyrian drought in the eastern Mediterranean and Middle East (2.7-2.5 kyr BP; Kathayat et al., 2019), the Mauria Empire (2.1-1.9 kyr BP), and the Guge Kingdom (0.9-0.3 kyr BP) pluvials in India and Tibet (Kathayat et al., 2017). A secular shift toward drier conditions since 0.5 kyr BP in the Siddha Baba record tracks the 18O records from Dasuopu glacier, Nepal Himalaya, and Sahiya cave, North India. Numerous multidecadal oscillations are also evident, including markedly wetter conditions during the 18th century, in the late Little Ice Age, apparent in the Dasuopu and Sahiya records. References Adhikari et al. (2020) Tellus B: Chem. Phys. Meteor., 72, 1-17. Kathayat et al. (2017) Sc. Adv., 7, e1701296. Kathayat et al. (2019) Sci. Adv., 5, eaax6656.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1609/aaai.v37i13.26841
