Reconstruction of global surface ocean <i>p</i>CO<sub>2</sub> using region-specific predictors based on a stepwise FFNN regression algorithm

نویسندگان

چکیده

Abstract. Various machine learning methods were attempted in the global mapping of surface ocean partial pressure CO2 (pCO2) to reduce uncertainty sink estimate due undersampling pCO2. In previous research, predictors pCO2 usually selected empirically based on theoretic drivers pCO2, and same combination was applied all areas except where there a lack coverage. However, differences between different regions not considered. this work, we combined stepwise regression algorithm feed-forward neural network (FFNN) select mean absolute error each 11 biogeochemical provinces defined by self-organizing map (SOM) method. Based selected, monthly 1∘ × product from January 1992 August 2019 constructed. Validation combinations Surface Ocean Atlas (SOCAT) dataset version 2020 independent observations time series stations carried out. The prediction region-specific FFNN more precise than that research. Applying size-improving province decreased (MAE) 11.32 µatm root square (RMSE) 17.99 µatm. script file are distributed through Institute Oceanology Chinese Academy Sciences Marine Science Data Center (IOCAS, https://doi.org/10.12157/iocas.2021.0022, Zhong, 2021.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Impact of Novel Incorporation of CT-based Segment Mapping into a Conjugated Gradient Algorithm on Bone SPECT Imaging: Fundamental Characteristics of a Context-specific Reconstruction Method

Objective(s): The latest single-photon emission computed tomography (SPECT)/computed tomography (CT) reconstruction system, referred to as xSPECT Bone™, is a context-specific reconstruction system utilizing tissue segmentation information from CT data, which is called a zone map. The aim of this study was to evaluate theeffects of zone-map enhancement incorporated into the ordered-subset conjug...

متن کامل

On stepwise regression

Given data y and k covariates x one problem in linear regression is to decide which in any of the covariates to include when regressing y on the x. If k is small it is possible to evaluate each subset of the x. If however k is large then some other procedure must be use. Stepwise regression and the lasso are two such procedures but they both assume a linear model with error term. A different ap...

متن کامل

EM-based stepwise regression imputation using standard and robust methods

Imputation of missing values is one of the major tasks for data pre-processing in many areas. Whenever imputation of data from official statistics comes into mind, several (additional) challenges almost always arise, like large data sets, data sets consisting of a mixture of different variable types, or data outliers. The aim of this contribution is to propose an automatic algorithm called IRMI...

متن کامل

Determining Effective Factors on Land Surface Temperature of Tehran Using LANDSAT Images And Integrating Geographically Weighted Regression With Genetic Algorithm

Due to urbanization and changes in the urban thermal environment and since the land surface temperature (LST) in urban areas are a few degrees higher than in surrounding non-urbanized areas, identifying spatial factors affecting on LST in urban areas is very important. Hence, by identifying these factors, preventing this phenomenon become possible using general education, inserting rules and al...

متن کامل

A Novel Scheme for Improving Accuracy of KNN Classification Algorithm Based on the New Weighting Technique and Stepwise Feature Selection

K nearest neighbor algorithm is one of the most frequently used techniques in data mining for its integrity and performance. Though the KNN algorithm is highly effective in many cases, it has some essential deficiencies, which affects the classification accuracy of the algorithm. First, the effectiveness of the algorithm is affected by redundant and irrelevant features. Furthermore, this algori...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Biogeosciences

سال: 2022

ISSN: ['1726-4189', '1726-4170']

DOI: https://doi.org/10.5194/bg-19-845-2022