Many process-based models for carbon flux predictions have faced a wide range of uncertainty issues. The complex interactions between the atmosphere and the forest ecosystems can lead to uncertainties in the model result. On the other hand, artificial intelligence (AI) techniques, which are novel methods to resolve complex and nonlinear problems, have shown a possibility for forest ecological applications. This study is the first step to present an objective comparison between multiple AI models for the daily forest gross primary productivity (GPP) prediction using satellite remote sensing data. We built the AI models such as support vector machine (SVM), random forest (RF), artificial neural network (ANN), and deep neural network (DNN) using in-situ observations from an eddy covariance (EC) flux tower and satellite remote sensing data such as albedo, aerosol, temperature, and vegetation index. We focused on the Gwangneung site from the Korea Regional Flux Network (KoFlux) in South Korea, 2006–2015. As a result, the DNN model outperformed the other three models through an intensive hyperparameter optimization, with the correlation coefficient (CC) of 0.93 and the mean absolute error (MAE) of 0.68 g m⁻² d⁻¹ in a 10-fold blind test. We showed that the DNN model also performed well under conditions of cold waves, heavy rain, and an autumnal heatwave. As future work, a comprehensive comparison with the result of process-based models will be necessary using a more extensive EC database from various forest ecosystems.

Accurate estimate of the seasonal leaf area index (LAI) in croplands is required for understanding not only intra- and inter-annual crop development, but also crop management. Lack of consideration in different growth phases in the relationship between LAI and vegetation indices (VI) often results in unsatisfactory estimation in the seasonal course of LAI. In this study, we partitioned the growing season into two phases separated by maximum VI ( ${\mathrm{VI}}_{\max }$ ) and applied the general regression model to the data gained from two phases. As an alternative method to capture the influence of seasonal phenological development on the LAI-VI relationship, we developed a consistent development curve method and compared its performance with the general regression approaches. We used the Normalized Difference VI (NDVI) and the Enhanced VI (EVI) from the rice paddy sites in Asia (South Korea and Japan) and Europe (Spain) to examine its applicability across different climate conditions and management cycles. When the general regression method was used, separating the season into two phases resulted in no better estimation than the estimation obtained with the entire season observation due to an abrupt change in seasonal LAI occurring during the transition between the before and after ${\mathrm{VI}}_{\max }$ . The consistent development curve method reproduced the seasonal patterns of LAI from both NDVI and EVI across all sites better than the general regression method. Despite less than satisfactory estimation of a local ${\mathrm{LAI}}_{\max }$ , the consistent development curve method demonstrates improvement in estimating the seasonal course of LAI. The method can aid in providing accurate seasonal LAI as an input into ecological process-based models.

Mangroves are critical to global carbon mitigation efforts due to their exceptional carbon sequestration capacity, but they also provide a wide range of additional ecosystem services including coastal protection, water purification, and also socio-economic benefits such as fishing and recreation. However, research on mangrove ecosystem services often focuses primarily on carbon sequestration, with limited attention to other critical functions. In this review, we analyze the co-occurrence of multiple ecosystem services studied alongside carbon sequestration and highlight the need for a more comprehensive approach to mangrove ecosystem management. A search yielded 813 relevant studies, with 423 of which were further analyzed. Only about 22% of studies investigated more than one service, providing limited insight into the relationships between multiple ecosystem services. The most studied ecosystem services with carbon sequestration were regulating services, namely nutrient cycling followed by soil formation and coastal protection. Provisioning services such as fishing and biomass, and cultural services such as recreation were also studied but less. Also, stakeholder engagement remains minimal, with only 5% of studies incorporating perspectives from local communities, policymakers, or other relevant groups. Given the expected expansion of mangrove ecosystems due to climate change, it is crucial to consider both ecological and social dimensions when developing management strategies. We propose a socio-ecological framework to integrate other ecosystem services alongside carbon sequestration. By broadening the scope of mangrove ecosystem studies, we can promote more inclusive, effective, and sustainable management approaches that benefit both nature and society.

Understanding productivity in agricultural ecosystems is important, as it plays a significant role in modifying regional carbon balances and capturing carbon in the form of agricultural yield. This study in particular combines information from flux determinations using the eddy covariance (EC) methodology, process‐based modeling of carbon gain, remotely (satellite) sensed vegetation indices (VIs), and field surveys to assess the gross primary production (GPP) of rice, which is a primary food crop worldwide. This study relates two major variables determining GPP. The first is leaf area index (LAI) and carboxylation capacity of the rice canopy (Vc_uptake), and the second being MODIS remotely sensed vegetation indices (VIs). Success in applying such derived relationships has allowed GPP to be remotely determined over the seasonal course of rice development. The relationship to VIs of both LAI and Vc_uptake was analyzed first by using the regression approaches commonly applied in remote sensing studies. However, the resultant GPP estimations derived from these generic models were not consistently accurate and led to a large proportion of underestimations. The new, alternative approach developed to estimate LAI and Vc_uptake uses consistent development curves for rice (i.e., relies on consistent biological regulations of plant development). The modeled GPP based on this consistent development curve for both LAI and Vc_uptake agreed with R² from 0.76 to 0.92 (within the 95% confidence interval). The results of this study demonstrate that improved linkages between ground‐based survey data, eddy flux measurements, process‐based models, and remote sensing data can be constructed to estimate GPP in rice paddies. This study suggests further that the conceptual application of the consistent development curve, such as the combining of different scale measurements, has the potential to predict GPP better than the common practice of utilizing simple linear models, when seeking to estimate the critical parameters that influence carbon gain and agricultural yields.