Artificial intelligence for geoscience: Progress, challenges and perspectives

The Innovation, Год журнала: 2024, Номер 5(5), С. 100691 - 100691

Опубликована: Авг. 23, 2024

Public summary•What does AI bring to geoscience? has been accelerating and deepening our understanding of Earth Systems in an unprecedented way, including the atmosphere, lithosphere, hydrosphere, cryosphere, biosphere, anthroposphere interactions between spheres.•What are noteworthy challenges As we embrace huge potential geoscience, several arise reliability interpretability, ethical issues, data security, high demand cost.•What is future The synergy traditional principles modern AI-driven techniques holds immense promise will shape trajectory geoscience upcoming years.AbstractThis paper explores evolution geoscientific inquiry, tracing progression from physics-based models data-driven approaches facilitated by significant advancements artificial intelligence (AI) collection techniques. Traditional models, which grounded physical numerical frameworks, provide robust explanations explicitly reconstructing underlying processes. However, their limitations comprehensively capturing Earth's complexities uncertainties pose optimization real-world applicability. In contrast, contemporary particularly those utilizing machine learning (ML) deep (DL), leverage extensive glean insights without requiring exhaustive theoretical knowledge. ML have shown addressing science-related questions. Nevertheless, such as scarcity, computational demands, privacy concerns, "black-box" nature hinder seamless integration into geoscience. methodologies hybrid presents alternative paradigm. These incorporate domain knowledge guide methodologies, demonstrate enhanced efficiency performance with reduced training requirements. This review provides a comprehensive overview research paradigms, emphasizing untapped opportunities at intersection advanced It examines major showcases advances large-scale discusses prospects that landscape outlines dynamic field ripe possibilities, poised unlock new understandings further advance exploration.Graphical abstract

Язык: Английский

---

First close insight into global daily gapless 1 km PM2.5 pollution, variability, and health impact

Nature Communications, Год журнала: 2023, Номер 14(1)

Опубликована: Дек. 15, 2023

Abstract Here we retrieve global daily 1 km gapless PM 2.5 concentrations via machine learning and big data, revealing its spatiotemporal variability at an exceptionally detailed level everywhere every day from 2017 to 2022, valuable for air quality monitoring, climate change, public health studies. We find that 96%, 82%, 53% of Earth’s populated areas are exposed unhealthy least one day, week, month in respectively. Strong disparities exposure risks duration exhibited between developed developing countries, urban rural areas, different parts cities. Wave-like dramatic changes clearly seen around the world before, during, after COVID-19 lockdowns, as is mortality burden linked fluctuating pollution events. Encouragingly, only approximately one-third all countries return pre-pandemic levels. Many nature-induced episodes also revealed, such biomass burning.

Язык: Английский

---

Long-term mortality burden trends attributed to black carbon and PM2·5 from wildfire emissions across the continental USA from 2000 to 2020: a deep learning modelling study

The Lancet Planetary Health, Год журнала: 2023, Номер 7(12), С. e963 - e975

Опубликована: Дек. 1, 2023

Long-term improvements in air quality and public health the continental USA were disrupted over past decade by increased fire emissions that potentially offset decrease anthropogenic emissions. This study aims to estimate trends black carbon PM

Язык: Английский

---

Long-term exposure to PM2.5 and its constituents and visual impairment in schoolchildren: A population-based survey in Guangdong province, China

Environment International, Год журнала: 2025, Номер 195, С. 109270 - 109270

Опубликована: Янв. 1, 2025

Exposure to fine particulate matter (PM2.5) has been linked visual impairment. Nevertheless, evidence associating PM2.5 constituents with impairment in schoolchildren is sparse. To explore the effects of long-term exposure and its on We conducted a large cross-sectional population-based study recruit 59,054 from four cities Guangdong province, China, used ChinaHighAirPollutants (CHAP) dataset estimate 3-year average concentrations (black carbon (BC), organic (OM), nitrate (NO3-), sulfate (SO42-) ammonium (NH4+)) based individuals' home addresses. Visual acuity was measured standardized logarithmic chart, defined as below 4.9 (Snellen 5/6 equivalent) at least one eye. utilized generalized linear mixed models weighted quantile sum regression assess association between The observed associations typically displayed nonlinear pattern. Compared lowest quartile constituents, fourth associated higher odds (e.g., adjusted ratio (OR) 1.23 (95% CI: 1.13, 1.33) for PM2.5, 1.53 1.40, 1.67) OM, 1.35 1.27, 1.44) BC), respectively. Similarly, joint (OR = 1.17, 95% 1.22), while BC OM contributed more associations. Long-term significantly rates schoolchildren, combustion-related potentially driving

Язык: Английский

---

Exposure to Fine Particulate Matter Constituents and Human Semen Quality Decline: A Multicenter Study

Environmental Science & Technology, Год журнала: 2023, Номер 57(35), С. 13025 - 13035

Опубликована: Авг. 22, 2023

Exposure to fine particulate matter (PM < 2.5 μm in diameter [PM2.5]) may accelerate human sperm quality decline, although research on this association is limited. Our objective was investigate the relationship between exposure chemical constituents of PM2.5 air pollution and decreased further explore exposure-response relationship. We conducted a multicenter population-based cohort study including 78,952 semen samples from 33,234 donors at 6 provincial banks (covering central, northern, southern, eastern, southwestern parts China) 2014 2020. Daily composition estimated using deep learning model integrating density ground-based measure network 1 km resolution. Linear mixed models with subject- center-specific intercepts were used quantify harmful impacts their relationships. Per interquartile range (IQR) increase levels during spermatogenesis significantly associated concentration, progressive motility, total motility. For constituents, per IQR increment Cl- (β: -0.02, 95% CI: [-0.03, -0.00]) NO3- -0.05, [-0.08, -0.02]) negatively count, while NH4+ -0.03, [-0.06, linked These results suggest that adversely affect quality, highlighting urgent need reduce exposure.

Язык: Английский

---

Spatiotemporal patterns and drivers of the urban air pollution island effect for 2273 cities in China

Environment International, Год журнала: 2024, Номер 184, С. 108455 - 108455

Опубликована: Янв. 21, 2024

Air pollution levels tend to be higher in urban areas than surrounding rural areas, and this air has a negative effect on human health. However, the spatiotemporal patterns of urban-rural differences determinants these remain unclear. Here, we calculate Urban Pollution Island (UAPI) intensity for PM2.5 PM10 monthly, seasonal, annual scale 2273 cities China from 2000 2020. Subsequently, analyze influence characteristics using combined approach two-way fixed effects model spatial Durbin model. Results show strong downward trend UAPI since 2013, with reductions ranging 42% 61% until 2020, both pollutants summer as well winter,.. Consistently, proportion experiencing phenomenon decreased 94.5% 77.3% PM10. We find significant morphology UAPI. Specifically, sprawl, polycentric development, an increase green spaces are associated reduction UAPI, while dense intensify it. Our study also reveals robust inverted U-shaped relationship between stages economic development Moreover, itself spillover that oppose their direct impacts. These results suggest regional planning more ambitious climate change mitigation policies could effective strategies mitigating end-of-pipe control.

Язык: Английский

---

Increased mortality risk from airborne exposure to polycyclic aromatic hydrocarbons

Journal of Hazardous Materials, Год журнала: 2024, Номер 474, С. 134714 - 134714

Опубликована: Май 23, 2024

Язык: Английский

---

Spatiotemporally continuous PM2.5 dataset in the Mekong River Basin from 2015 to 2022 using a stacking model

The Science of The Total Environment, Год журнала: 2024, Номер 914, С. 169801 - 169801

Опубликована: Янв. 4, 2024

Язык: Английский

---

Air pollution and risk of 32 health conditions: outcome-wide analyses in a population-based prospective cohort in Southwest China

BMC Medicine, Год журнала: 2024, Номер 22(1)

Опубликована: Сен. 11, 2024

Язык: Английский

---

High-resolution Simulation Dataset of Hourly PM2.5 Chemical Composition in China (CAQRA-aerosol) from 2013 to 2020

Advances in Atmospheric Sciences, Год журнала: 2025, Номер unknown

Опубликована: Янв. 22, 2025

Язык: Английский

---