2026-10-12T19:58:17Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34008294 2026-09-28T04:30:04Z category_62 portal_316 item_type_3 month_year_09_2026

Data Sheet 1_Estimating surface pCO2 and its long-term variability in the East China Sea using machine learning with satellite data.pdf Do-Hyeon Kwon (25119393) Young-Heon Jo (518000) JeongHee Shim (11550673) HuiTae Joo (12900665) Marine Biology air-sea CO2 flux East China Sea machine learning ocean colour sea surface pCO2 <p>Accurate estimation of sea surface partial pressure of CO₂ (pCO₂) in optically complex coastal waters remains challenging due to significant biogeochemical heterogeneity. This study develops a machine learning approach to reconstruct pCO₂ in the East China Sea (ECS) from 2003 to 2023, utilizing MODIS-derived optical classification. Using normalized water-leaving radiance at 555 nm (nL_w555) as a threshold (1.5 mW cm^-2µm^-1 sr^-1), the ECS was classified into two distinct regimes: Clear Water (CW) and Turbid Water (TW). Then, the pCO₂ was reconstructed using a Categorical Boosting (CatBoost) model that integrates multi-spectral satellite variables as numerical predictors with an optically-derived Water Case as a categorical input feature to account for heterogeneity. Evaluated on the test dataset, this approach achieved high overall accuracy (R² = 0.86, RMSE = 16.55 µatm), notably reducing prediction errors (RMSE) in TW by up to ~81% compared to conventional models. The model maintained robust regime-level generalization (CW: R² = 0.82, RMSE = 15.64 µatm; TW: R² = 0.82, RMSE = 22.01 µatm). The 21-year climatology reveals distinct mean pCO₂ levels for CW (361.2 µatm) and TW (415.1 µatm). While CW exhibits strong summer biological drawdown, TW functions as a highly variable net CO₂ source driven by positive non-thermal anomalies (+28.09 µatm). Over the 21-year period, the atmospheric CO₂ growth rate (+2.41 µatm yr^-1) significantly outpaced the surface pCO₂ increases in both regimes (CW: +0.66 µatm yr^-1; TW: +1.11 µatm yr^-1). This growing thermodynamic gradient overwhelmingly drives an increasingly negative flux anomaly (−0.182 mmol m^-2 d^-1 yr^-1), statistically intensifying the CW carbon sink. Crucially, recognizing the TW as a weak net source (+0.50 Tg C yr^-1) rather than a sink reveals that conventional models overestimate ECS carbon uptake by ~46% (~4.04 Tg C yr^-1). Ultimately, this study provides a highly refined long-term carbon budget for the ECS, demonstrating that accounting for spatial heterogeneity is key to accurately assessing coastal carbon dynamics.</p> 2026-09-28T04:30:04Z Dataset Dataset 10.3389/fmars.2026.1951665.s001 https://figshare.com/articles/dataset/Data_Sheet_1_Estimating_surface_pCO2_and_its_long-term_variability_in_the_East_China_Sea_using_machine_learning_with_satellite_data_pdf/34008294 CC BY 4.0