1
|
Mouatadid S, Orenstein P, Flaspohler G, Cohen J, Oprescu M, Fraenkel E, Mackey L. Adaptive bias correction for improved subseasonal forecasting. Nat Commun 2023; 14:3482. [PMID: 37321988 DOI: 10.1038/s41467-023-38874-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2022] [Accepted: 05/15/2023] [Indexed: 06/17/2023] Open
Abstract
Subseasonal forecasting-predicting temperature and precipitation 2 to 6 weeks ahead-is critical for effective water allocation, wildfire management, and drought and flood mitigation. Recent international research efforts have advanced the subseasonal capabilities of operational dynamical models, yet temperature and precipitation prediction skills remain poor, partly due to stubborn errors in representing atmospheric dynamics and physics inside dynamical models. Here, to counter these errors, we introduce an adaptive bias correction (ABC) method that combines state-of-the-art dynamical forecasts with observations using machine learning. We show that, when applied to the leading subseasonal model from the European Centre for Medium-Range Weather Forecasts (ECMWF), ABC improves temperature forecasting skill by 60-90% (over baseline skills of 0.18-0.25) and precipitation forecasting skill by 40-69% (over baseline skills of 0.11-0.15) in the contiguous U.S. We couple these performance improvements with a practical workflow to explain ABC skill gains and identify higher-skill windows of opportunity based on specific climate conditions.
Collapse
Affiliation(s)
- Soukayna Mouatadid
- Department of Computer Science, University of Toronto, Toronto, ON, Canada.
| | - Paulo Orenstein
- Instituto de Matemática Pura e Aplicada, Rio de Janeiro, Brazil
| | - Genevieve Flaspohler
- nLine Inc., Berkeley, CA, USA
- Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA
- Department of Applied Ocean Science and Engineering, Woods Hole Oceanographic Institution, Falmouth, MA, USA
| | - Judah Cohen
- Atmospheric and Environmental Research, Lexington, MA, USA
- Department of Civil and Environmental Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Miruna Oprescu
- Department of Computer Science, Cornell University, Ithaca, NY, USA
| | - Ernest Fraenkel
- Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
| | | |
Collapse
|
2
|
Liu C, Chen Y, Guo G, Zhao Q, Jiang H, Wu K, Peng Q, Chen Y, Fang D, Shen B, Shen H, Wu D, Sun H. Interpretable Machine Learning Model for Predicting Interaction Energies between Dimethyl Sulfide and Potential Absorbing Solvents. Ind Eng Chem Res 2023. [DOI: 10.1021/acs.iecr.2c04559] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/16/2023]
Affiliation(s)
- Chuanlei Liu
- School of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China
| | - Yuxiang Chen
- School of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China
| | - Guanchu Guo
- School of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China
| | - Qiyue Zhao
- School of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China
| | - Hao Jiang
- School of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China
| | - Kongguo Wu
- School of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China
| | - Qilong Peng
- School of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China
| | - Yu Chen
- School of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China
| | - Diyi Fang
- School of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China
| | - Benxian Shen
- School of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China
- International Joint Research Center of Green Energy Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China
| | - Haitao Shen
- International Joint Research Center of Green Energy Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China
| | - Di Wu
- Alexandra Navrotsky Institute for Experimental Thermodynamics, Washington State University, Pullman, Washington 99163, United States
- Gene and Linda Voiland School of Chemical Engineering and Bioengineering, Washington State University, Pullman, Washington 99163, United States
- Materials Science and Engineering, Washington State University, Pullman, Washington 99163, United States
- Department of Chemistry, Washington State University, Pullman, Washington 99163, United States
| | - Hui Sun
- School of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China
- International Joint Research Center of Green Energy Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China
| |
Collapse
|
3
|
Schmähling F, Martin J, Elster C. A framework for benchmarking uncertainty in deep regression. APPL INTELL 2022. [DOI: 10.1007/s10489-022-03908-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/02/2022]
Abstract
AbstractWe propose a framework for the assessment of uncertainty quantification in deep regression. The framework is based on regression problems where the regression function is a linear combination of nonlinear functions. Basically, any level of complexity can be realized through the choice of the nonlinear functions and the dimensionality of their domain. Results of an uncertainty quantification for deep regression are compared against those obtained by a statistical reference method. The reference method utilizes knowledge about the underlying nonlinear functions and is based on Bayesian linear regression using a prior reference. The flexibility, together with the availability of a reference solution, makes the framework suitable for defining benchmark sets for uncertainty quantification. Reliability of uncertainty quantification is assessed in terms of coverage probabilities, and accuracy through the size of calculated uncertainties. We illustrate the proposed framework by applying it to current approaches for uncertainty quantification in deep regression. In addition, results for three real-world regression tasks are presented.
Collapse
|
4
|
Conibear L, Reddington CL, Silver BJ, Chen Y, Knote C, Arnold SR, Spracklen DV. Sensitivity of Air Pollution Exposure and Disease Burden to Emission Changes in China Using Machine Learning Emulation. GEOHEALTH 2022; 6:e2021GH000570. [PMID: 35765412 PMCID: PMC9207901 DOI: 10.1029/2021gh000570] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/01/2022] [Revised: 05/09/2022] [Accepted: 05/16/2022] [Indexed: 06/15/2023]
Abstract
Machine learning models can emulate chemical transport models, reducing computational costs and enabling more experimentation. We developed emulators to predict annual-mean fine particulate matter (PM2.5) and ozone (O3) concentrations and their associated chronic health impacts from changes in five major emission sectors (residential, industrial, land transport, agriculture, and power generation) in China. The emulators predicted 99.9% of the variance in PM2.5 and O3 concentrations. We used these emulators to estimate how emission reductions can attain air quality targets. In 2015, we estimate that PM2.5 exposure was 47.4 μg m-3 and O3 exposure was 43.8 ppb, associated with 2,189,700 (95% uncertainty interval, 95UI: 1,948,000-2,427,300) premature deaths per year, primarily from PM2.5 exposure (98%). PM2.5 exposure and the associated disease burden were most sensitive to industry and residential emissions. We explore the sensitivity of exposure and health to different combinations of emission reductions. The National Air Quality Target (35 μg m-3) for PM2.5 concentrations can be attained nationally with emission reductions of 72% in industrial, 57% in residential, 36% in land transport, 35% in agricultural, and 33% in power generation emissions. We show that complete removal of emissions from these five sectors does not enable the attainment of the WHO Annual Guideline (5 μg m-3) due to remaining air pollution from other sources. Our work provides the first assessment of how air pollution exposure and disease burden in China varies as emissions change across these five sectors and highlights the value of emulators in air quality research.
Collapse
Affiliation(s)
- Luke Conibear
- School of Earth and EnvironmentInstitute for Climate and Atmospheric ScienceUniversity of LeedsLeedsUK
| | - Carly L. Reddington
- School of Earth and EnvironmentInstitute for Climate and Atmospheric ScienceUniversity of LeedsLeedsUK
| | - Ben J. Silver
- School of Earth and EnvironmentInstitute for Climate and Atmospheric ScienceUniversity of LeedsLeedsUK
| | - Ying Chen
- College of EngineeringMathematics and Physical SciencesUniversity of ExeterExeterUK
| | | | - Stephen R. Arnold
- School of Earth and EnvironmentInstitute for Climate and Atmospheric ScienceUniversity of LeedsLeedsUK
| | - Dominick V. Spracklen
- School of Earth and EnvironmentInstitute for Climate and Atmospheric ScienceUniversity of LeedsLeedsUK
| |
Collapse
|