skip to main content

Explore Research Products in the NSF-PAR

Title: Insight into cloud processes from unsupervised classification with a rotationally invariant autoencoder
Clouds play a critical role in the Earth's energy budget and their potential changes are one of the largest uncertainties in future climate projections. However, the use of satellite observations to understand cloud feedbacks in a warming climate has been hampered by the simplicity of existing cloud classification schemes, which are based on single-pixel cloud properties rather than utilizing spatial structures and textures. Recent advances in computer vision enable the grouping of different patterns of images without using human-predefined labels, providing a novel means of automated cloud classification. This unsupervised learning approach allows discovery of unknown climate-relevant cloud patterns, and the automated processing of large datasets. We describe here the use of such methods to generate a new AI-driven Cloud Classification Atlas (AICCA), which leverages 22 years and 800 terabytes of MODIS satellite observations over the global ocean. We use a rotation-invariant cloud clustering (RICC) method to classify those observations into 42 AI-generated cloud class labels at ~100 km spatial resolution. As a case study, we use AICCA to examine a recent finding of decreasing cloudiness in a critical part of the subtropical stratocumulus deck, and show that the change is accompanied by strong trends in cloud classes.  more » « less
Award ID(s):
1735359
NSF-PAR ID:
10486595
Author(s) / Creator(s):
; ; ; ;
Publisher / Repository:
Conference on Neural Information Processing -Machine Learning for Physical Science
Date Published:
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ( , Fire)
    In recent decades, wildfires in many areas of the United States (U.S.) have become larger and more frequent with increasing anthropogenic pressure, including interactions between climate, land-use change, and human ignitions. We aimed to characterize the spatiotemporal patterns of contemporary fire characteristics across the contiguous United States (CONUS). We derived fire variables based on frequency, fire radiative power (FRP), event size, burned area, and season length from satellite-derived fire products and a government records database on a 50 km grid (1984–2020). We used k-means clustering to create a hierarchical classification scheme of areas with relatively homogeneous fire characteristics, or modern ‘pyromes,’ and report on the model with eight major pyromes. Human ignition pressure provides a key explanation for the East-West patterns of fire characteristics. Human-dominated pyromes (85% mean anthropogenic ignitions), with moderate fire size, area burned, and intensity, covered 59% of CONUS, primarily in the East and East Central. Physically dominated pyromes (47% mean anthropogenic ignitions) characterized by relatively large (average 439 mean annual ha per 50 km pixel) and intense (average 75 mean annual megawatts/pixel) fires occurred in 14% of CONUS, primarily in the West and West Central. The percent of anthropogenic ignitions increased over time in all pyromes (0.5–1.7% annually). Higher fire frequency was related to smaller events and lower FRP, and these relationships were moderated by vegetation, climate, and ignition type. Notably, a spatial mismatch between our derived modern pyromes and both ecoregions and historical fire regimes suggests other major drivers for modern U.S. fire patterns than vegetation-based classification systems. This effort to delineate modern U.S. pyromes based on fire observations provides a national-scale framework of contemporary fire regions and may help elucidate patterns of change in an uncertain future. 
    more » « less
  2. ; ; ; ; ; ; ; ( , Environmental Data Science)
    Abstract Atmospheric aerosols influence the Earth’s climate, primarily by affecting cloud formation and scattering visible radiation. However, aerosol-related physical processes in climate simulations are highly uncertain. Constraining these processes could help improve model-based climate predictions. We propose a scalable statistical framework for constraining the parameters of expensive climate models by comparing model outputs with observations. Using the C3.AI Suite, a cloud computing platform, we use a perturbed parameter ensemble of the UKESM1 climate model to efficiently train a surrogate model. A method for estimating a data-driven model discrepancy term is described. The strict bounds method is applied to quantify parametric uncertainty in a principled way. We demonstrate the scalability of this framework with 2 weeks’ worth of simulated aerosol optical depth data over the South Atlantic and Central African region, written from the model every 3 hr and matched in time to twice-daily MODIS satellite observations. When constraining the model using real satellite observations, we establish constraints on combinations of two model parameters using much higher time-resolution outputs from the climate model than previous studies. This result suggests that within the limits imposed by an imperfect climate model, potentially very powerful constraints may be achieved when our framework is scaled to the analysis of more observations and for longer time periods. 
    more » « less
  3. ; ; ( , The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences)

    Abstract. Permafrost thaw has been observed at several locations across the Arctic tundra in recent decades; however, the pan-Arctic extent and spatiotemporal dynamics of thaw remains poorly explained. Thaw-induced differential ground subsidence and dramatic microtopographic transitions, such as transformation of low-centered ice-wedge polygons (IWPs) into high-centered IWPs can be characterized using very high spatial resolution (VHSR) commercial satellite imagery. Arctic researchers demand for an accurate estimate of the distribution of IWPs and their status across the tundra domain. The entire Arctic has been imaged in 0.5 m resolution by commercial satellite sensors; however, mapping efforts are yet limited to small scales and confined to manual or semi-automated methods. Knowledge discovery through artificial intelligence (AI), big imagery, and high performance computing (HPC) resources is just starting to be realized in Arctic science. Large-scale deployment of VHSR imagery resources requires sophisticated computational approaches to automated image interpretation coupled with efficient use of HPC resources. We are in the process of developing an automated Mapping Application for Permafrost Land Environment (MAPLE) by combining big imagery, AI, and HPC resources. The MAPLE uses deep learning (DL) convolutional neural nets (CNNs) algorithms on HPCs to automatically map IWPs from VHSR commercial satellite imagery across large geographic domains. We trained and tasked a DLCNN semantic object instance segmentation algorithm to automatically classify IWPs from VHSR satellite imagery. Overall, our findings demonstrate the robust performances of IWP mapping algorithm in diverse tundra landscapes and lay a firm foundation for its operational-level application in repeated documentation of circumpolar permafrost disturbances.

     
    more » « less
  4. ; ; ; ; ( , Advances in Atmospheric Sciences)
    Abstract The Southern Ocean is covered by a large amount of clouds with high cloud albedo. However, as reported by previous climate model intercomparison projects, underestimated cloudiness and overestimated absorption of solar radiation (ASR) over the Southern Ocean lead to substantial biases in climate sensitivity. The present study revisits this long-standing issue and explores the uncertainty sources in the latest CMIP6 models. We employ 10-year satellite observations to evaluate cloud radiative effect (CRE) and cloud physical properties in five CMIP6 models that provide comprehensive output of cloud, radiation, and aerosol. The simulated longwave, shortwave, and net CRE at the top of atmosphere in CMIP6 are comparable with the CERES satellite observations. Total cloud fraction (CF) is also reasonably simulated in CMIP6, but the comparison of liquid cloud fraction (LCF) reveals marked biases in spatial pattern and seasonal variations. The discrepancies between the CMIP6 models and the MODIS satellite observations become even larger in other cloud macro- and micro-physical properties, including liquid water path (LWP), cloud optical depth (COD), and cloud effective radius, as well as aerosol optical depth (AOD). However, the large underestimation of both LWP and cloud effective radius (regional means ∼20% and 11%, respectively) results in relatively smaller bias in COD, and the impacts of the biases in COD and LCF also cancel out with each other, leaving CRE and ASR reasonably predicted in CMIP6. An error estimation framework is employed, and the different signs of the sensitivity errors and biases from CF and LWP corroborate the notions that there are compensating errors in the modeled shortwave CRE. Further correlation analyses of the geospatial patterns reveal that CF is the most relevant factor in determining CRE in observations, while the modeled CRE is too sensitive to LWP and COD. The relationships between cloud effective radius, LWP, and COD are also analyzed to explore the possible uncertainty sources in different models. Our study calls for more rigorous calibration of detailed cloud physical properties for future climate model development and climate projection. 
    more » « less
  5. ; ; ; ; ; ; ( , Journal of Hydrometeorology)
    Abstract

    Accurate and timely precipitation estimates are critical for monitoring and forecasting natural disasters such as floods. Despite having high-resolution satellite information, precipitation estimation from remotely sensed data still suffers from methodological limitations. State-of-the-art deep learning algorithms, renowned for their skill in learning accurate patterns within large and complex datasets, appear well suited to the task of precipitation estimation, given the ample amount of high-resolution satellite data. In this study, the effectiveness of applying convolutional neural networks (CNNs) together with the infrared (IR) and water vapor (WV) channels from geostationary satellites for estimating precipitation rate is explored. The proposed model performances are evaluated during summer 2012 and 2013 over central CONUS at the spatial resolution of 0.08° and at an hourly time scale. Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks (PERSIANN)–Cloud Classification System (CCS), which is an operational satellite-based product, and PERSIANN–Stacked Denoising Autoencoder (PERSIANN-SDAE) are employed as baseline models. Results demonstrate that the proposed model (PERSIANN-CNN) provides more accurate rainfall estimates compared to the baseline models at various temporal and spatial scales. Specifically, PERSIANN-CNN outperforms PERSIANN-CCS (and PERSIANN-SDAE) by 54% (and 23%) in the critical success index (CSI), demonstrating the detection skills of the model. Furthermore, the root-mean-square error (RMSE) of the rainfall estimates with respect to the National Centers for Environmental Prediction (NCEP) Stage IV gauge–radar data, for PERSIANN-CNN was lower than that of PERSIANN-CCS (PERSIANN-SDAE) by 37% (14%), showing the estimation accuracy of the proposed model.

     
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email