Hydrological Response to Climate Change: McGAN for Multi-Site Scenario Weather Series Generation and LSTM for Streamflow Modeling DOI Creative Commons
Jian Sha,

Yaxin Chang,

Yaxiu Liu

et al.

Atmosphere, Journal Year: 2024, Volume and Issue: 15(11), P. 1348 - 1348

Published: Nov. 9, 2024

This study focuses on the impacts of climate change hydrological processes in watersheds and proposes an integrated approach combining a weather generator with multi-site conditional generative adversarial network (McGAN) model. The incorporates ensemble GCM predictions to generate regional average synthetic series, while McGAN transforms these averages into spatially consistent data. By addressing spatial consistency problem generating this tackles key challenge site-scale impact assessment. Applied Jinghe River Basin west-central China, generated daily temperature precipitation data for four stations under different shared socioeconomic pathways (SSP1-26, SSP2-45, SSP3-70, SSP5-85) up 2100. These were then used long short-term memory (LSTM) network, trained historical data, simulate river flow from 2021 results show that (1) effectively addresses correlation generation; (2) future is likely increase flow, particularly high-emission scenarios; (3) frequency extreme events may increase, proactive policies can mitigate flood drought risks. offers new tool hydrologic–climatic assessment studies.

Language: Английский

Pushing the frontiers in climate modelling and analysis with machine learning DOI
Veronika Eyring, William D. Collins, Pierre Gentine

et al.

Nature Climate Change, Journal Year: 2024, Volume and Issue: 14(9), P. 916 - 928

Published: Aug. 23, 2024

Language: Английский

Citations

32
A Performance Comparison Study on Climate Prediction in Weifang City Using Different Deep Learning Models DOI Open Access
Qingchun Guo,

Zhenfang He,

Zhaosheng Wang

et al.

Water, Journal Year: 2024, Volume and Issue: 16(19), P. 2870 - 2870

Published: Oct. 9, 2024

Climate change affects the water cycle, resource management, and sustainable socio-economic development. In order to accurately predict climate in Weifang City, China, this study utilizes multiple data-driven deep learning models. The data for 73 years include monthly average air temperature (MAAT), minimum (MAMINAT), maximum (MAMAXAT), total precipitation (MP). different models artificial neural network (ANN), recurrent NN (RNN), gate unit (GRU), long short-term memory (LSTM), convolutional (CNN), hybrid CNN-GRU, CNN-LSTM, CNN-LSTM-GRU. CNN-LSTM-GRU MAAT prediction is best-performing model compared other with highest correlation coefficient (R = 0.9879) lowest root mean square error (RMSE 1.5347) absolute (MAE 1.1830). These results indicate that method a suitable model. This can also be used surface modeling. will help flood control management.

Language: Английский

Citations

10
The need for carbon-emissions-driven climate projections in CMIP7 DOI Creative Commons
Benjamin M. Sanderson, Ben Booth, John P. Dunne

et al.

Geoscientific model development, Journal Year: 2024, Volume and Issue: 17(22), P. 8141 - 8172

Published: Nov. 19, 2024

Abstract. Previous phases of the Coupled Model Intercomparison Project (CMIP) have primarily focused on simulations driven by atmospheric concentrations greenhouse gases (GHGs), for both idealized model experiments and climate projections different emissions scenarios. We argue that although this approach was practical to allow parallel development Earth system detailed socioeconomic futures, carbon cycle uncertainty as represented diverse, process-resolving models (ESMs) is not manifested in scenario outcomes, thus omitting a dominant source meeting Paris Agreement. Mitigation policy defined terms human activity (including emissions), with strategies varying their timing net-zero emissions, balance mitigation effort between short-lived long-lived forcers, reliance land use strategy, extent removals. To explore response these drivers, ESMs need explicitly represent complete cycles major GHGs, including natural processes anthropogenic influences. Carbon removal sequestration strategies, which rely proposed management systems, are currently calculated integrated assessment (IAMs) during only net passed ESM. However, proper accounting coupled impacts feedback such interventions requires explicit process representation build self-consistent physical representations potential effectiveness risks under change. propose CMIP7 efforts prioritize CO2 from fossil fuel projected deployment dioxide technologies, well management, using resolution allowed state-of-the-art resolve carbon–climate feedbacks. Post-CMIP7 ambitions should aim incorporate modeling non-CO2 GHGs (in particular, sources sinks methane nitrous oxide) process-based options. These developments will three primary benefits: (1) resources be allocated policy-relevant better real-time information related detectability verification reductions relationship expected near-term impacts, (2) range possible future states feedbacks increasingly well-represented ESMs, (3) optimal utilization strengths wider context infrastructure (which includes simple models, machine learning approaches kilometer-scale models).

Language: Английский

Citations

9
Monitoring and Modeling the Soil‐Plant System Toward Understanding Soil Health DOI Creative Commons
Yijian Zeng, Anne Verhoef, Harry Vereecken

et al.

Reviews of Geophysics, Journal Year: 2025, Volume and Issue: 63(1)

Published: Jan. 25, 2025

Abstract The soil health assessment has evolved from focusing primarily on agricultural productivity to an integrated evaluation of biota and biotic processes that impact properties. Consequently, shifted a predominantly physicochemical approach incorporating ecological, biological molecular microbiology indicators. This shift enables comprehensive exploration microbial community properties their responses environmental changes arising climate change anthropogenic disturbances. Despite the increasing availability indicators (physical, chemical, biological) data, holistic mechanistic linkage not yet been fully established between functions across multiple spatiotemporal scales. article reviews state‐of‐the‐art monitoring, understanding how soil‐microbiome‐plant contribute feedback mechanisms causes in properties, as well these have functions. Furthermore, we survey opportunities afforded by soil‐plant digital twin approach, integrative framework amalgamates process‐based models, Earth Observation data assimilation, physics‐informed machine learning, achieve nuanced comprehension health. review delineates prospective trajectory for monitoring embracing systematically observe model system. We further identify gaps opportunities, provide perspectives future research enhanced intricate interplay hydrological processes, hydraulics, microbiome, landscape genomics.

Language: Английский

Citations

0
Summary and future prospects DOI
M. Rajeevan, P. Mukhopadhyay, Arindam Chakraborty

et al.

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 315 - 332

Published: Jan. 1, 2025

Language: Английский

Citations

0
The futures of climate modeling DOI Creative Commons

Stefano Bordoni,

S. M. Kang,

Tiffany A. Shaw

et al.

npj Climate and Atmospheric Science, Journal Year: 2025, Volume and Issue: 8(1)

Published: March 12, 2025

Language: Английский

Citations

0
Synergistic policy effects of digitization in reducing air pollution and addressing climate change in China DOI
Weidong Chen,

Shing Tsung Hu,

Yong Liu

et al.

Journal of Environmental Management, Journal Year: 2025, Volume and Issue: 380, P. 124730 - 124730

Published: March 17, 2025

Language: Английский

Citations

0
AI in public administration-transformative opportunities for climate resilience and sustainable development DOI Creative Commons
María E. Raygoza-L., Jesús Heriberto Orduño-Osuna, Gabriel Trujillo-Hernández

et al.

Revista de Ciencias Tecnológicas, Journal Year: 2025, Volume and Issue: 8(2), P. 1 - 21

Published: April 3, 2025

The accelerated growth in demands for natural resources such as water and energy has generated a potential crisis, while the requirements have been hastily driven by development of emerging technologies that spanned various sectors, so intersection these technologies, Artificial Intelligence (AI), sustainability, governance public policies, offers transformative opportunities to combat climate change promote sustainable development. This study explores integration AI administration resilience, equity innovation, highlights applications resource management, disaster prediction, renewable optimization planning. sustainable, highlighting priority role ethical frameworks public-private collaborations ensure equitable transparent deployment AI. Challenges data accessibility, allocation adjacent regulatory balance are analyzed with strategies overcome them, including capacity infrastructure investment. innovative findings suggest tool efficiently managed action helps address environmental challenges, key elements through requires collaborative between stakeholders, those across integrating principles into management policies. integrated approach positions fundamental more future.

Language: Английский

Citations

0
Peptide Property Prediction for Mass Spectrometry Using AI: An Introduction to State of the Art Models DOI Creative Commons

Jesse Angelis,

Eva Ayla Schröder, Zixuan Xiao

et al.

PROTEOMICS, Journal Year: 2025, Volume and Issue: unknown

Published: April 10, 2025

ABSTRACT This review explores state of the art machine learning and deep models for peptide property prediction in mass spectrometry‐based proteomics, including, but not limited to, predicting digestibility, retention time, charge distribution, collisional cross section, fragmentation ion intensities, detectability. The combination these enables only silico generation spectral libraries also finds many additional use cases design targeted assays or data‐driven rescoring. serves as both an introduction newcomers update experienced researchers aiming to develop accessible reproducible predictions. Key limitations current models, including difficulties handling diverse post‐translational modifications instrument variability, highlight need large‐scale, harmonized datasets, standardized evaluation metrics benchmarking.

Language: Английский

Citations

0
Projections of future climate for U.S. national assessments: past, present, future DOI Creative Commons
Samantha Basile, Allison Crimmins, Fredric Lipschultz

et al.

Climatic Change, Journal Year: 2025, Volume and Issue: 178(4)

Published: April 1, 2025

Climate assessments consolidate our understanding of possible future climate conditions as represented by projections, which are largely based on the output global models. Over past 30 years, scientific insights gained from projections have been refined through model structural improvements, emerging constraints feedbacks, and increased computational efficiency. Within same period, process assessing evaluating information has become more defined targeted to inform users. As size audience expanded, framing, relevancy, accessibility increasingly important. This paper reviews use in national (NCA) while highlighting challenges opportunities that identified over time. Reflections lessons learned address continuous understand broadening assessment evolving user needs. Insights for NCA development include (1) identifying benchmarks standards downscaled datasets, (2) expanding efforts gather research gaps needs how presented (3) providing practitioner guidance use, interpretation, reporting uncertainty better decision-making.

Language: Английский

Citations

0