Andrew Geiss

The relationship between cloud droplet number concentration (Nd) and liquid water path (LWP) is highly uncertain yet crucial for determining the impact of aerosol-cloud interactions (ACI) on Earth's radiation budget. The Nd-LWP relationship is examined using a machine learning (ML) random forest model applied to five years of satellite data at grid resolutions ranging from 10° to 0.05° in 12 distinct regions. In the subtropics, the shape of the Nd-LWP relationship switches from an inverted-V at 1° grid-resolution to an “M” shape at 0.1° resolution with decreased sensitivity. Tropical and midlatitude regions generally show a more positive sensitivity. Cloud sampling and filtering also influence this slope, wherein the exclusion of thin clouds, as commonly performed to reduce retrieval uncertainty, leads to strongly negative sensitivity across all regions. Precipitation is primarily responsible for driving the strength of the sensitivity, with strong positive slopes in raining clouds and negative and/or neutral responses found in non-raining clouds. A new method to compute radiative forcing from the ML model shows a robust Twomey radiative forcing across all regions and grid resolutions. However, LWP and cloud fraction adjustments to the radiative forcing, which are ∼50 % or smaller than the Twomey effect, decrease to negligible values with higher spatial resolution data. As Earth system models move toward higher spatial resolutions in the future, evaluating the LWP and CF adjustment contributions to the radiative forcing budget at these finer resolutions will be essential for evaluation and model development.

The direct interactions of atmospheric aerosols with radiation significantly impact the Earth's climate and weather and are important to represent accurately in simulations of the atmosphere. This work introduces two contributions to enable a more accurate representation of aerosol optics in atmosphere models: (1) NeuralMie, a neural network Mie scattering emulator that can directly compute the bulk optical properties of a diverse range of aerosol populations and is appropriate for use in atmosphere simulations where aerosol optical properties are parameterized, and (2) TAMie, a fast Python-based Mie scattering code based on the Mie scattering algorithm that can represent both homogeneous and coated particles. TAMie achieves speed and accuracy comparable to established Fortran Mie codes and is used to produce training data for NeuralMie. NeuralMie is highly flexible and can be used for a wide range of particle types, wavelengths, and mixing assumptions. It can represent core-shell scattering and, by directly estimating bulk optical properties, is more efficient than existing Mie code and Mie code emulators while incurring negligible error compared to existing aerosol optics parameterization schemes (0.08 % mean absolute percentage error).

Marine boundary layer clouds are crucial in Earth's climate system. They frequently manifest as closed or open cell mesoscale cellular convection (MCC). MCC clouds are challenging to represent accurately in current climate models, highlighting the need for detailed observational data sets and in-depth analyses. This study utilizes over 8 years of observations from the U.S. Department of Energy (DOE) Atmospheric Radiation Measurement (ARM) User Facility Eastern North Atlantic (ENA) site at Graciosa Island, Azores, to investigate these clouds. We first apply a convolutional neural network with a U-Net architecture to classify open and closed cells, marking the first application of such an approach for automatically detecting MCC patterns from ground-based radar measurements. This method addresses some observational gaps in satellite data related to low temporal resolution, nighttime challenges, and limited vertical structure capture. The analysis of the MCC cases shows clear differences between closed and open MCCs: Closed MCC clouds are characterized by lower cloud tops and bases, shallower cloud geometrical depth, weaker horizontal wind speeds, stronger atmospheric stability, and a more homogeneous liquid water path than open MCCs. Finally, we demonstrate two potential applications of our radar-based MCC classifications: (a) facilitating the investigation of aerosol-cloud interactions and (b) exploring meteorological factors along with MCC's evolution by integrating satellite imagery and back-trajectory analysis. The identified MCC cases offer a valuable resource for the scientific community to study MCC processes further and improve climate model accuracy.

This study examines how different structural choices in bulk microphysics schemes impact the simulation of warm rain initiation. A single liquid category (SLC) approach prognosing up to four moments of a single drop size distribution (DSD) is compared to the traditional two-category, two-moment approach with separate DSDs for cloud and rain (four total prognostic variables). Different methods for calculating tendencies of the prognostic variables from drop collision-coalescence are also tested: a discretized numerical-integration approach, machine learning via neural networks, lookup tables, and traditional power law fits. Relative to simulations using a bin microphysics model, SLC gives smaller error overall than the two-category approach when numerical integration is used to calculate the collision-coalescence tendencies for both. Replacing the numerical integration with a pre-computed lookup table reduces computational cost with little loss of accuracy. However, using fitted power laws with SLC to represent the collision-coalescence tendencies substantially reduces accuracy and leads to an order of magnitude increase in error. It is also demonstrated that with SLC, reasonably accurate solutions are obtained using only three prognostic moments, while a two-moment SLC scheme leads to substantial error. Overall, both the choice of prognostic moments (e.g., SLC vs. two-category) and method to calculate the collision-coalescence tendencies are important to consider for minimizing errors in bulk schemes. SLC with a sufficiently detailed calculation of the collision-coalescence tendencies provides accurate solutions for a reasonable computational cost, providing a viable alternative to the traditional two-category, two-moment approach for bulk microphysics.

Due to their persistent widespread severe winds, derechos pose significant threats to human safety and property, with impacts comparable to many tornadoes and hurricanes. Yet, automated detection of derechos remains challenging due to the absence of spatiotemporally continuous observations and the complex criteria employed to define the phenomenon. This study presents an objective derecho detection approach capable of automatically identifying derechos through both observations and model results. The approach is grounded in a physically based definition of derechos and integrates three algorithms: (1) the Python Flexible Object Tracker (PyFLEXTRKR) algorithm to track mesoscale convective systems (MCSs), (2) a semantic segmentation convolutional neural network to identify bow echoes, and (3) a comprehensive classification algorithm to detect derechos within MCS life cycles and distinguish derecho-producing from non-derecho-producing MCSs. Using this approach, we developed a novel high-resolution (4 km and hourly) observational dataset of derechos and accompanying derecho-producing MCSs over the United States east of the Rocky Mountains from 2004 to 2021. The dataset consists of two subsets based on different gust speed data sources and is analyzed to document the climatology of derechos in the United States. On average, 12–15 derechos are identified per year, aligning with previous estimations (∼6–21 events annually). The spatial distribution and seasonal variation patterns are consistent with prior studies, showing peak occurrences in the Great Plains and the Midwest during the warm season. Additionally, during the study period, derechos account for approximately 3.1 % of measured damaging gusts (≥25.93 m s−1) over the eastern United States. The dataset is publicly available at https://doi.org/10.5281/zenodo.14835362 (Li et al., 2025).

Vertically resolved thermodynamic cloud-phase classifications are essential for studies of atmospheric cloud and precipitation processes. The Department of Energy (DOE) Atmospheric Radiation Measurement (ARM) Thermodynamic Cloud Phase (THERMOCLDPHASE) value-added product (VAP) uses a multi-sensor approach to classify the thermodynamic cloud phase by combining lidar backscatter and depolarization, radar reflectivity, Doppler velocity, spectral width, microwave-radiometer-derived liquid water path, and radiosonde temperature measurements. The measured pixels are classified as ice, snow, mixed phase, liquid (cloud water), drizzle, rain, and liq_driz (liquid+drizzle). We use this product as the ground truth to train three machine learning (ML) models to predict the thermodynamic cloud phase from multi-sensor remote sensing measurements taken at the ARM North Slope of Alaska (NSA) observatory: a random forest (RF), a multi-layer perceptron (MLP), and a convolutional neural network (CNN) with a U-Net architecture. Evaluations against the outputs of the THERMOCLDPHASE VAP with 1 year of data show that the CNN outperforms the other two models, achieving the highest test accuracy, F1 score, and mean intersection over union (IOU). Analysis of ML confidence scores shows that ice, rain, and snow have higher confidence scores, followed by liquid, while mixed, drizzle, and liq_driz have lower scores. Feature importance analysis reveals that the mean Doppler velocity and vertically resolved temperature are the most influential data streams for ML thermodynamic cloud-phase predictions. Lidar measurements exhibit lower feature importance due to rapid signal attenuation caused by the frequent presence of persistent low-level clouds at the NSA site. The ML models' generalization capacity is further evaluated by applying them at another Arctic ARM site in Norway using data taken during the ARM Cold-Air Outbreaks in the Marine Boundary Layer Experiment (COMBLE) field campaign. The models demonstrated similar performance to that observed at the NSA site. Finally, we evaluate the ML models' response to simulated instrument outages and signal degradation and show that a CNN U-Net model trained with input channel dropouts performs better when input fields are missing.

Low-level marine clouds play a pivotal role in Earth’s weather and climate through their interactions with radiation, heat and moisture transport, and the hydrological cycle. These interactions depend on a range of dynamical and microphysical processes that result in a broad diversity of cloud types and spatial structures, and a comprehensive understanding of cloud morphology is critical for continued improvement of our atmospheric modeling and prediction capabilities moving forward. Deep learning has recently accelerated our ability to study clouds using satellite remote sensing, and machine learning classifiers have enabled detailed studies of cloud morphology. A major limitation of deep learning approaches to this problem, however, is the large number of hand-labeled samples that are required for training. This work applies a recently developed self-supervised learning scheme to train a deep convolutional neural network (CNN) to map marine cloud imagery to vector embeddings that capture information about mesoscale cloud morphology and can be used for satellite image classification. The model is evaluated against existing cloud classification datasets and several use cases are demonstrated, including training cloud classifiers with very few labeled samples, interrogation of the CNN’s learned internal feature representations, cross-instrument application, and resilience against sensor calibration drift and changing scene brightness. The self-supervised approach learns meaningful internal representations of cloud structures and achieves comparable classification accuracy to supervised deep learning methods without the expense of creating large hand-annotated training datasets.

The depth of convective clouds affects vertical transport of atmospheric constituents, influencing downstream weather and climate. Atmospheric controls on the maximum depth reached by moist convection are investigated with radar-tracked convective cells tagged with sounding-derived atmospheric parameters from a field campaign in central Argentina. Regression analyses show that narrow (<12-km diameter) and wide (>16-km diameter) cell depths respond to disparate factors, where cell areas are defined using composite reflectivity signatures. Undiluted lifted parcel indices including convective available potential energy (CAPE) and level of neutral buoyancy (LNB) are top predictors of wide cell maximum depth while mid-tropospheric relative humidity is the top predictor of narrow cell maximum depth. Because narrow cells are more numerous than wide cells, the overall outcome of the full cell population does not strongly correlate with CAPE and LNB conditions. Tracked cells and atmospheric conditions in a simulation with 3-km grid spacing covering the field campaign produce similar results to those observed. Narrow cells that are relatively deep have a cooler and moister mid-troposphere with weaker free tropospheric subsidence, while relatively deep wide cells have much warmer and moister lower tropospheric conditions. These atmospheric differences are present 1 hr before cell initiation at both a fixed observing site and variable cell initiation locations. Simulated narrow cell maximum equivalent potential temperature decreases with height at a rate similar to the ambient vertical gradient, causing these cells to fall short of their LNB and supporting the view that entrainment-driven dilution is a dominant control on their depth.

CloudSat’s Cloud Profiling Radar is a valuable tool for remotely monitoring high-latitude snowfall, but its ability to observe hydrometeor activity near the Earth’s surface is limited by a radar blind zone caused by ground clutter contamination. This study presents the development of a deeply supervised U-Net-style convolutional neural network to predict cold season reflectivity profiles within the blind zone at two Arctic locations. The network learns to predict the presence and intensity of near-surface hydrometeors by coupling latent features encoded in blind zone-aloft clouds with additional context from collocated atmospheric state variables (i.e., temperature, specific humidity, and wind speed). Results show that the U-Net predictions outperform traditional linear extrapolation methods, with low mean absolute error, a 38% higher Sørensen–Dice coefficient, and vertical reflectivity distributions 60% closer to observed values. The U-Net is also able to detect the presence of near-surface cloud with a critical success index (CSI) of 72% and cases of shallow cumuliform snowfall and virga with 18% higher CSI values compared to linear methods. An explainability analysis shows that reflectivity information throughout the scene, especially at cloud edges and at the 1.2-km blind zone threshold, along with atmospheric state variables near the tropopause, are the most significant contributors to model skill. This surface-trained generative inpainting technique has the potential to enhance current and future remote sensing precipitation missions by providing a better understanding of the nonlinear relationship between blind zone reflectivity values and the surrounding atmospheric state.

Atmospheric aerosols have a substantial impact on climate and remain one of the largest sources of uncertainty in climate prediction. Accurate representation of their direct radiative effects is a crucial component of modern climate models. However, direct computation of the radiative properties of aerosol populations is far too computationally expensive to perform in a climate model, so optical properties are typically approximated using a parameterization. This work develops artificial neural networks (ANNs) capable of replacing the current aerosol optics parameterization used in the Energy Exascale Earth System Model (E3SM). A large training dataset is generated by using Mie code to directly compute the optical properties of a range of atmospheric aerosol populations given a large variety of particle sizes, wavelengths, and refractive indices. Optimal neural architectures for shortwave and longwave bands are identified by evaluating ANNs with randomly generated wirings. Randomly generated deep ANNs are able to outperform conventional multilayer-perceptron-style architectures with comparable parameter counts. Finally, the ANN-based parameterization produces significantly more accurate bulk aerosol optical properties than the current parameterization when compared with direct Mie calculations using mean absolute error. The success of this approach makes possible the future inclusion of much more sophisticated representations of aerosol optics in climate models that cannot be captured by extension of the existing parameterization scheme and also demonstrates the potential of random-wiring-based neural architecture search in future applications in the Earth sciences.

Exploring the climate impacts of various anthropogenic emissions scenarios is key to making informed decisions for climate change mitigation and adaptation. State-of-the-art Earth system models can provide detailed insight into these impacts but have a large associated computational cost on a per-scenario basis. This large computational burden has driven recent interest in developing cheap machine learning models for the task of climate model emulation. In this paper, we explore the efficacy of randomly wired neural networks for this task. We describe how they can be constructed and compare them with their standard feedforward counterparts using the ClimateBench dataset. Specifically, we replace the serially connected dense layers in multilayer perceptrons, convolutional neural networks, and convolutional long short-term memory networks with randomly wired dense layers and assess the impact on model performance for models with 1 million and 10 million parameters. We find that models with less-complex architectures see the greatest performance improvement with the addition of random wiring (up to 30.4% for multilayer perceptrons). Furthermore, of 24 different model architecture, parameter count, and prediction task combinations, only one had a statistically significant performance deficit in randomly wired networks relative to their standard counterparts, with 14 cases showing statistically significant improvement. We also find no significant difference in prediction speed between networks with standard feedforward dense layers and those with randomly wired layers. These findings indicate that randomly wired neural networks may be suitable direct replacements for traditional dense layers in many standard models.

Recent advances in deep convolutional neural network (CNN)-based super resolution can be used to downscale atmospheric chemistry simulations with substantially higher accuracy than conventional downscaling methods. This work both demonstrates the downscaling capabilities of modern CNN-based single image super resolution and video super-resolution schemes and develops modifications to these schemes to ensure they are appropriate for use with physical science data. The CNN-based video super-resolution schemes in particular incur only 39 % to 54 % of the grid-cell-level error of interpolation schemes and generate outputs with extremely realistic small-scale variability based on multiple perceptual quality metrics while performing a large (8×10) increase in resolution in the spatial dimensions. Methods are introduced to strictly enforce physical conservation laws within CNNs, perform large and asymmetric resolution changes between common model grid resolutions, account for non-uniform grid-cell areas, super-resolve lognormally distributed datasets, and leverage additional inputs such as high-resolution climatologies and model state variables. High-resolution chemistry simulations are critical for modeling regional air quality and for understanding future climate, and CNN-based downscaling has the potential to generate these high-resolution simulations and ensembles at a fraction of the computational cost.

Missing and low-quality data regions are a frequent problem for weather radars. They stem from a variety of sources: beam blockage, instrument failure, near-ground blind zones, and many others. Filling in missing data regions is often useful for estimating local atmospheric properties and the application of high-level data processing schemes without the need for preprocessing and error-handling steps – feature detection and tracking, for instance. Interpolation schemes are typically used for this task, though they tend to produce unrealistically spatially smoothed results that are not representative of the atmospheric turbulence and variability that are usually resolved by weather radars. Recently, generative adversarial networks (GANs) have achieved impressive results in the area of photo inpainting. Here, they are demonstrated as a tool for infilling radar missing data regions. These neural networks are capable of extending large-scale cloud and precipitation features that border missing data regions into the regions while hallucinating plausible small-scale variability. In other words, they can inpaint missing data with accurate large-scale features and plausible local small-scale features. This method is demonstrated on a scanning C-band and vertically pointing Ka-band radar that were deployed as part of the Cloud Aerosol and Complex Terrain Interactions (CACTI) field campaign. Three missing data scenarios are explored: infilling low-level blind zones and short outage periods for the Ka-band radar and infilling beam blockage areas for the C-band radar. Two deep-learning-based approaches are tested, a convolutional neural network (CNN) and a GAN that optimize pixel-level error or combined pixel-level error and adversarial loss respectively. Both deep-learning approaches significantly outperform traditional inpainting schemes under several pixel-level and perceptual quality metrics.