Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Mechanistic Models: Compartment Models in Individual and Population Analysis01:23

Mechanistic Models: Compartment Models in Individual and Population Analysis

27
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
27
Steps in Outbreak Investigation01:18

Steps in Outbreak Investigation

105
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
105

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Aluminum mineral transformation drives reacidification and metal remobilization in a neutralized acidic pit lake.

Water research·2026
Same author

Commonality and variability in functional networks in children under 5 years old.

Communications biology·2026
Same author

Apatite-doped cyanobacterial biochar for treating smelting site pollution: A "win-win" strategy for cyanobacteria resource recovery and heavy metal mitigation.

Environmental geochemistry and health·2026
Same author

The role of long non-coding RNA HCP5 in ulcerative cutaneous tuberculosis therapy introduction.

Frontiers in cellular and infection microbiology·2026
Same author

<i>In vitro</i> interspecies interactions between methicillin-resistant <i>Staphylococcus aureus</i> and <i>Pseudomonas aeruginosa</i>: effects on bacterial growth, antibiotic susceptibility, and transcriptomic reprogramming.

Frontiers in cellular and infection microbiology·2026
Same author

Time trend of sugar-sweetened beverages intake from 2002 to 2022 among adults in Beijing, China.

Preventive medicine reports·2026

Related Experiment Video

Updated: Jun 5, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

500

Utilizing large language models for identifying future research opportunities in environmental science.

Xiaoliang Ji1, Xinyue Wu2, Rui Deng3

  • 1Zhejiang Provincial Key Laboratory of Watershed Science and Health, School of Public Health, Wenzhou Medical University, Wenzhou, 325035, China.

Journal of Environmental Management
|December 14, 2024
PubMed
Summary

Large language models (LLMs) can identify emerging research topics in environmental science. The GPT-3.5 API offers a comprehensive analysis of cutting-edge environmental science, aiding researchers in addressing global challenges.

Keywords:
Artificial intelligenceChatGPTEnvironmental scienceGPT-4Large language models

More Related Videos

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM
12:26

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM

Published on: October 11, 2016

13.3K
Watershed Planning within a Quantitative Scenario Analysis Framework
12:44

Watershed Planning within a Quantitative Scenario Analysis Framework

Published on: July 24, 2016

8.0K

Related Experiment Videos

Last Updated: Jun 5, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

500
Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM
12:26

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM

Published on: October 11, 2016

13.3K
Watershed Planning within a Quantitative Scenario Analysis Framework
12:44

Watershed Planning within a Quantitative Scenario Analysis Framework

Published on: July 24, 2016

8.0K

Area of Science:

  • Environmental science research
  • Interdisciplinary studies
  • Climate change and pollution research

Background:

  • Environmental science faces challenges in identifying innovative research topics.
  • Traditional bibliometrics struggle with nascent interdisciplinary fields.
  • Artificial intelligence (AI) offers potential solutions for identifying research gaps.

Purpose of the Study:

  • To explore the capabilities of large language models (LLMs) in identifying emerging research opportunities in environmental science.
  • To analyze the effectiveness of different LLM APIs (GPT-3.5, ChatGPT, GPT-4) for this task.
  • To highlight the role of AI and big data in addressing environmental challenges.

Main Methods:

  • Utilized a text retrieval method based on word embeddings.
  • Employed emergent reasoning abilities of LLMs combined with embedded search techniques.
  • Dynamically integrated the latest literature for analysis.
  • Compared the GPT-3.5 API with supplementary literature, ChatGPT, and GPT-4.

Main Results:

  • The GPT-3.5 API provided a more comprehensive, detailed, and current analysis compared to other tested LLMs.
  • LLMs demonstrate potential in identifying nascent interdisciplinary fields and knowledge gaps.
  • Timeliness and dynamics of the field are crucial for effective research topic identification.

Conclusions:

  • LLMs are valuable tools for researchers seeking guidance and inspiration in environmental science.
  • Interdisciplinary research, AI, and big data are critical for tackling urgent global environmental challenges.
  • The GPT-3.5 API shows promise for advanced environmental science research analysis.