Artificial Intelligence (AI) and Machine Learning are assisting the U.S. Office of Science in analysing sea- and bay-breeze circulations from the Gulf of Mexico and Galveston Bay during the summer months. In southeastern Texas, breezes play an important role in weather and storm development.
These circulations influence the flow of moisture and aerosol particles into the Houston region in conjunction with larger-scale weather systems called synoptic conditions. Thus, moisture and aerosol influence the formation of thunderstorms and the linked rainfall. Understanding how these flows impact clouds and storms is critical for improving weather forecasting and climate modelling techniques.
The correlations between weather system circulations and cloud physics in southeastern Texas are divulged using artificial intelligence advanced algorithms in the study. The results provide essential insights into the region’s variability of these regions’ circulations and allow researchers to isolate the effects of circulations on aspects of the region’s climate, such as storm formation, aerosol impact, and other factors.
These discoveries are assisting researchers in narrowing the focus of their study on the aerosol and cloud life cycle, aerosol-cloud interactions, and air quality during the Department of Energy (DOE) Atmospheric Radiation Measurement (ARM) user facility’s Tracking Aerosol Convection Interactions ExpeRiment (TRACER) field campaign in the Houston area in 2021 and 2022.
Moreover, during the summer months (June-September), the researchers exercised Self-Organising Map (SOM), an unsupervised machine learning approach, to classify synoptic regimes in the southeastern Texas region. Brookhaven National Laboratory, Pennsylvania State University, Purdue University, SUNY Geneseo, Stony Brook University, and Cornell University were all represented on the team.
The SOM was used to identify three dominating synoptic regimes. The study spans ten years, with a continuum of transitional phases of 700-hPa geopotential height anomalies from reanalysis data. The principal regimes are as follows:
- A pre-trough regime associated with a synoptic trough to the northwest of the region
- A post-trough regime connected with the northerly upper-level flow
- An anticyclonic regime within the westward reach of the Bermuda High
To investigate the characteristics of cloud and precipitation properties (e.g., fraction, intensity) in different regimes, the team projected data from the Geostationary Operational Environmental Satellite and the Next-Generation Weather Radar system onto each SOM node. Due to significant moisture advection, when southeastern Texas is positioned in the southwest quadrant of a high-pressure maritime system, the region experiences increased cloud frequency during the afternoon hours.
A convergence of synoptic southerly flow and sea-breeze circulation frequently characterises this regime. When a high-pressure system passes over southeastern Texas, large-scale subsidence dominates, with weak pressure gradients and moderate precipitable water vapour. This weak synoptic forcing is favourable for forming sea breezes. It is supported by increased onshore flow, the lower surface temperature in the early afternoon, and a sharp increase in radar echo top height.
Singapore used a similar digital transformation strategy. The National Environment Agency (NEA) and the Singapore Land Authority (SLA) have signed a Memorandum of Understanding (MoU) to explore the use of Global Navigation Satellite System (GNSS) data from SLA’s Singapore Satellite Reference Network (SiReNT).
This moves aims to assist the NEA in better monitoring the island’s atmospheric moisture. The partnership’s five-year mission is to help Singapore with weather monitoring by providing additional data and making exploratory studies for weather forecasting easier.
According to the MoU, SiReNT will include MSS’s GNSS station, providing MSS with continuous, near-real-time atmospheric moisture readings for the whole island. This non-conventional moisture data will supplement MSS’s present observation network data and enable study into future uses for weather forecasting by providing higher resolution and more frequent observation data.
Furthermore, the SiReNT technology promotes innovation in various industries, including autonomous driving, logistics and automation in the construction industry, and monitoring of changes in Singapore’s land height and sea level.