Surendra Bhatta | Search NASA

NASA NTRS2023

Diagnosis of Antarctic Blowing Snow Properties Using MERRA-2 Reanalysis with a Machine Learning Model

This paper presents the work on using a machine learning model to diagnose Antarctic blowing snow (BLSN) properties with the Modern Era Retrospective analysis for Research and Applications v2 (MERRA-2) data. We adopt the random forest classifier for BLSN identification and the random forest regressor for BLSN optical depth and height diagnosis. BLSN properties observed from the Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) are used as the truth for training the model. Using MERRA-2 fields such as snow age, surface elevation and pressure, temperature, specific humidity, and temperature gradient at the 2m level, and wind speed at the 10m level as input, reasonable results are achieved. Hourly blowing snow property diagnostics are generated with the trained model. Using the year 2010 as an example, it is shown that the Antarctic BLSN frequency is much higher over East than West Antarctica. High frequency months are from April to September, during which BLSN frequency exceeds 20% over East Antarctica. For May 2010, the BLSN snow frequency in the region is as high as 37%. Due to the suppression by strong surface-based inversions, larger values of BLSN height and optical depth are usually limited to the coastal regions, wherein the strength of surface-based inversions is weaker.

Antarctic↗

NASA NTRS2023

Reconstructing PM 2.5 Data Record for the Kathmandu Valley Using a Machine Learning Model

This paper presents a method for reconstructing the historical hourly concentrations of particulate matter 2.5 (PM2.5) over the Kathmandu Valley from 1980 to the present. The method uses a machine learning model that is trained using PM2.5 readings from US Embassy (Phora Durbar) as a ground truth, and the meteorological data from Modern-Era Retrospective Analysis for Research and Applications v2 (MERRA2) as input. The Extreme Gradient Boosting (XGBoost) model acquires a credible 10-fold cross-validation (CV) score of ~83.4%, an r2-score of ~84%, a Root Mean Square Error (RMSE) of ~15.82 µg/m3, and a Mean Absolute Error (MAE) of ~10.27 µg/m3. Further demonstrating the model's applicability to years other than those for which truth values are unavailable, the multiple cross-test with an unseen data set offered r2-scores for 2018, 2019, and 2020 ranging from 56% to 67%. The model-predicted data agrees with true values and indicates that MERRA2 underestimates PM2.5 over the region. It strongly agrees with ground-based evidence showing substantially higher mass concentrations in the dry pre- and post-monsoon seasons than in the monsoon months. It also shows a strong anti-correlation between PM2.5 concentration and humidity. The results also demonstrate that none of the years fulfilled the annual mean air quality index (AQI) standards set by the World Health Organization (WHO).

machine learning↗

NASA NTRS2023

Three-Wavelength Approach for Aerosol-Cloud Discrimination in the Sage III/ISS Aerosol Extinction Dataset

The tropical upper troposphere and lower stratosphere (UTLS) region is dominated by aerosols and clouds affecting Earth’s radiation budget and climate. Thus, satellites’ continuous monitoring and identification of these layers is crucial for quantifying their radiative impact. However, distinguishing between aerosols and clouds is challenging, especially under the perturbed UTLS conditions during post-volcanic eruptions and wildfire events. Aerosol-cloud discrimination is primarily based on their disparate wavelength-dependent scattering and absorption properties. In this study, we use aerosol extinction observations in the tropical (15°N-15°S) UTLS from June 2017 to February 2021, available from the latest generation of the Stratospheric Aerosol and Gas Experiment (SAGE) instrument-SAGE III onboard the International Space Station (ISS) to study aerosols and clouds. During this period, the SAGE III/ISS provided better coverage over the tropics at additional wavelength channels (relative to previous SAGE missions) and witnessed several volcanic and wildfire events that perturbed the tropical UTLS. We explore the advantage of having an extinction coefficient at an additional wavelength channel (1550 nm) from the SAGE III/ISS in aerosol-cloud discrimination using a method based on thresholds of two extinction coefficient ratios, R1R1 (520 nm/1020 nm) and R2R2 (1020 nm/1550 nm). This method was proposed earlier by Kent et al. [Appl. Opt. 36, 8639 (1997) [CrossRef] ] for the SAGE III-Meteor-3M but was never tested for the tropical region under volcanically perturbed conditions. We call this method the Extinction Color Ratio (ECR) method. The ECR method is applied to the SAGE III/ISS aerosol extinction data to obtain cloud-filtered aerosol extinction coefficients, cloud-top altitude, and seasonal cloud occurrence frequency during the entire study period. Cloud-filtered aerosol extinction coefficient obtained using the ECR method revealed the presence of enhanced aerosols in the UTLS following volcanic eruptions and wildfire events consistent with the Ozone Mapping and Profiler Suite (OMPS) and space-borne lidar-Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP). The cloud-top altitude obtained from the SAGE III/ISS is within 1 km of the nearly co-located observations from OMPS and CALIOP. In general, the seasonal mean cloud-top altitude from the SAGE III/ISS events peaks during the December, January, and February months, with sunset events showing higher cloud tops than the sunrise events, indicating the seasonal and diurnal variation of the tropical convection. The seasonal altitude distribution of cloud occurrence frequency obtained from the SAGE III/ISS also agrees well with CALIOP observations within 10%. We show that the ECR method is a simple approach that relies on thresholds independent of the sampling period, providing cloud-filtered aerosol extinction coefficients uniformly for climate studies irrespective of the UTLS conditions. However, since the predecessor of SAGE III did not include a 1550 nm channel, the usefulness of this approach is limited to short-term climate studies after 2017.

Clouds Aerosols↗