Data-driven method for the improving forecasts of local weather dynamics

Krivec, Tadej; Kocijan, Juš; Perne, Matija; Grašič, Boštjan; Božnar, Marija Zlata; Mlakar, Primož

doi:10.1016/j.engappai.2021.104423

Cited by 11 publications

(7 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These models can be used to comprehend the fundamental dynamics of the physical components of the natural climate phenomena, derive global temporal and spatial changes, and make predictions based on the future greenhouse gases emissions 25 . Differences between simulations and observations are often expected, with significant differences usually caused by numerical approximations, nonlinear behaviors, unresolved small-scale processes, and variability in data 26 – 28 . Therefore, the projections of the physical models can range widely 29 .…”

Section: Introductionmentioning

confidence: 99%

“…Unlike physical models, data-based models often suffer from data inconsistency and absence more severely. Machine learning methods, including deep learning, have been applied to examine global climate change recently 28 , 30 , 31 , 41 , 44 . However, machine learning methods are often regarded as black boxes, with the model’s underlying dynamics unseen to the users.…”

Section: Introductionmentioning

confidence: 99%

“…Differences between simulations and observations are often expected, with significant differences usually caused by numerical approximations, nonlinear behaviors, unresolved small-scale processes, and variability in data [26][27][28] . Therefore, the projections of the physical models can range widely 29 .…”

mentioning

confidence: 99%

See 2 more Smart Citations

Data driven pathway analysis and forecast of global warming and sea level rise

Song

Tong

Chao

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Climate change is a critical issue of our time, and its causes, pathways, and forecasts remain a topic of broader discussion. In this paper, we present a novel data driven pathway analysis framework to identify the key processes behind mean global temperature and sea level rise, and to forecast the magnitude of their increase from the present to 2100. Based on historical data and dynamic statistical modeling alone, we have established the causal pathways that connect increasing greenhouse gas emissions to increasing global mean temperature and sea level, with its intermediate links encompassing humidity, sea ice coverage, and glacier mass, but not for sunspot numbers. Our results indicate that if no action is taken to curb anthropogenic greenhouse gas emissions, the global average temperature would rise to an estimated 3.28 °C (2.46–4.10 °C) above its pre-industrial level while the global sea level would be an estimated 573 mm (474–671 mm) above its 2021 mean by 2100. However, if countries adhere to the greenhouse gas emission regulations outlined in the 2021 United Nations Conference on Climate Change (COP26), the rise in global temperature would lessen to an average increase of 1.88 °C (1.43–2.33 °C) above its pre-industrial level, albeit still higher than the targeted 1.5 °C, while the sea level increase would reduce to 449 mm (389–509 mm) above its 2021 mean by 2100.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Data driven pathway analysis and forecast of global warming and sea level rise

Song

Tong

Chao

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The CNAAA is installed at Itaorna Beach, a coastal region with a narrow continental strip at the bottom of Ilha Grande Bay (Figure 2). In addition, the plant is surrounded by the Serra do Mar mountain range, formed by high mountains and hills with high declivity [23], as shown in Figure 2. The physiographic characteristics of the region provide the formation of local circulations of sea/land and valley/mountain breezes, in addition to orographic gravity waves [65].…”

Section: Study Areamentioning

confidence: 99%

“…In environmental planning and management of nuclear operations, high resolution observational network, geotechnologies, numerical weather prediction and radionuclide dispersion modeling integrated systems are used (e.g., [22,23]). Measurements are the primary approach to better understand the atmosphere and they may also be used to investigate if model simulations properly describe the environment [24].…”

Section: Introductionmentioning

confidence: 99%

Thermally and Dynamically Driven Atmospheric Circulations over Heterogeneous Atmospheric Boundary Layer: Support for Safety Protocols and Environment Management at Nuclear Central Areas

et al. 2021

View full text Add to dashboard Cite

Ilha Grande Bay is located in Angra dos Reis, Rio de Janeiro State, Brazil. The area is characterized by different land cover, complex topography and proximity to the Atlantic Ocean. These aspects make it susceptible to thermally and dynamically induced atmospheric circulations such as those associated with valley/mountain and land/sea breeze systems, among others. The Almirante Álvaro Alberto Nuclear Complex (CNAAA) is located in this region, with a total of two nuclear power plants (NPPs) in operation in the Brazilian territory, Angra I and Angra II. Therefore, knowledge of local atmospheric circulation has become a matter of national and international security. Considering the importance of the meteorological security tool as a support for licensing, installation, routine operation and nuclear accident mitigation, the main aim of this study is the development of combined strategies of environmental statistical modeling in the analysis of thermally and dynamically driven atmospheric circulations over mountainous and coastal environments. We identified and hierarchized the influence of the thermally and mechanically driven forcing on the wind regime and stability conditions in the coastal atmospheric boundary layer over the complex topography region. A meteorological network of ground-based instruments was used along with physiographic information for the observational characterization of the atmospheric patterns in the spatial and time–frequency domain. The predominant wind directions and intensity are attributed to the combined action of multiscale weather systems, notably, the valley/mountain and continent/ocean breeze circulations, the forced channeling due to valley axis orientation, the influence of the synoptic scale systems and atmospheric thermal tide. The observational investigation of the combined influence of terrain effects and meteorological systems aimed to understand the local atmospheric circulation serves as support for safety protocols of the NPPs, contemplating operation and environmental management. The importance of the study for the adequacy and skill evaluation of computational modeling systems for atmospheric dispersion of pollutants such as radionuclide and conventional contaminants can be also highlighted, in order that such systems are used as tools for environmental planning and managing nuclear operations, particularly those located in regions over mountainous and coastal environments with a heterogeneous atmospheric boundary layer.

show abstract