Although the troposphere is often considered the layer of the atmosphere closest to the Earth's surface, the planetary boundary layer (CLP) – the lowest layer of the troposphere – is actually the part that most influences significantly affects weather conditions near the surface. In 2018 ten-year survey of planetary sciencesthe PBL was created as a important scientific question this has the potential to improve storm forecasting and climate projections.
“The PBL is where the surface interacts with the atmosphere, including moisture and heat exchanges that help cause weathering and climate change,” explains Adam Milstein, technical staff member at the Applied Space Group Systems at Lincoln Laboratory. “The PBL is also where humans live, and the turbulent movement of aerosols through the PBL is important for air quality that influences human health.”
Although vital for the study of weather and climate, important features of the PBL, such as its height, are difficult to resolve with current technology. For the past four years, Lincoln Lab staff have studied PBL, focusing on two different tasks: using machine learning to create 3D-scanned profiles of the atmosphere and more clearly resolving the vertical structure of the atmosphere. atmosphere in order to better predict droughts. .
This PBL-focused research effort builds on more than a decade of related work on fast, operational neural network algorithms developed by Lincoln Laboratory for NASA missions. These missions include time-resolved observations of precipitation structure and storm intensity with a constellation of small satellites (TROPICS) as well as Aqua, a satellite that collects data on Earth's water cycle and observes variables such as ocean temperature, precipitation and water vapor in the atmosphere. These algorithms retrieve temperature and humidity data from satellite instruments and have been shown to significantly improve the accuracy and usable global coverage of observations compared to previous approaches. For TROPICS, the algorithms help retrieve data used to characterize the rapidly evolving structures of a storm in near real time, and for Aqua, they have helped augment forecast models, drought monitoring, and fire forecasting.
These operational algorithms for TROPICS and Aqua are based on classic “shallow” neural networks to maximize speed and simplicity, creating a one-dimensional vertical profile for each spectral measurement collected by the instrument at each location. Although this approach has improved observations of the atmosphere down to the surface as a whole, including the PBL, laboratory staff have determined that new “deep” learning techniques treating the atmosphere from a region of interest as a three-dimensional image are necessary to enhance the details of the PBL. further away.
“We hypothesized that deep learning and artificial intelligence (AI) techniques could improve current approaches by incorporating into solutions better statistical representation of 3D imaging of temperature and humidity of the atmosphere,” Milstein explains. “But it took some time to figure out how to create the best data set – a mix of real and simulated data; we had to prepare ourselves to train these techniques.
The team collaborated with Joseph Santanello of NASA's Goddard Space Flight Center and William Blackwell, also of the Applied Space Systems Group, on a recent study. NASA-funded effort showing that these retrieval algorithms can improve the details of the PBL, including more accurate determination of the PBL height than the previous state of the art.
Although increased knowledge of PBL is widely useful in improving understanding of climate and weather, a key application is drought forecasting. According to a Global Drought Snapshot Report published last year, droughts are an urgent global problem that the global community must address. The lack of surface humidity, particularly at the PBL level, is the main indicator of drought. Although previous studies using remote sensing techniques have examined soil moisture To determine drought risk, studying the atmosphere can help predict when droughts will occur.
Part of an effort funded by the Lincoln Laboratory Climate Change Initiative, Milstein and lab staff member Michael Pieper are working with scientists at NASA's Jet Propulsion Laboratory (JPL) to use neural network techniques to improve prediction of droughts over the continental United States. Although the work builds on existing operational work done by JPL by integrating (in part) the lab's “shallow” neural network operational approach for Aqua, the team believes that this work and research on Deep learning focused on PBL can be combined to further improve. the accuracy of drought forecasting.
“Lincoln Lab has worked with NASA for more than a decade on neural network algorithms to estimate atmospheric temperature and humidity from space-based infrared and microwave instruments, including those at spaceship Aqua,” says Milstein. “During this time, we have learned a lot about this problem by working with the scientific community, including learning about the scientific challenges that remain. Our long experience working on this type of remote sensing with NASA scientists, as well as our experience using neural network techniques, has given us a unique perspective.
According to Milstein, the next step in this project is to compare the deep learning results to National Oceanic and Atmospheric Administration, NASA and Department of Energy datasets collected directly in the PBL using radiosondes, a type of instrument flown at a meteorological site. ball. “These direct measurements can be considered as a kind of ‘ground truth’ to quantify the precision of the techniques we have developed,” explains Milstein.
This improved neural network approach promises to demonstrate drought prediction that can exceed the capabilities of existing indicators, Milstein says, and provide a tool that scientists can rely on for decades to come.