Estimation of CO2 flux components over northern hemisphere forest ecosystems by using random forest method through temporal and spatial data scanning procedures.

Modeling CO2 flux components is an important task in ecosystem analysis and terrestrial studies. Net ecosystem exchange (NEE), ecosystem respiration (R), and gross primary production (GPP) are three CO2 flux components. Despite the ecosystem land cover characteristics, climatic factors can make considerable impact on quantity and mechanism of these components. Nevertheless, such climatic factors are not available in most of the areas, especially in developing regions. Therefore, obtaining the models that can exempt using locally recorded variables would be of great importance. A modeling study was carried out here to simulate CO2 flux components using soft computing-based random forest (RF) model in both local and external (spatial) scales, assessed by k-fold validation procedure. Data from 11 sites located in three forest ecosystems, e.g. deciduous broad leaf (DBF), evergreen needle leaf (ENF), and mixed forest (MF), were used to simulate the flux components. The obtained results showed that the temperature-related parameters (e.g., air and soil temperature, vapor pressure deficit) along with the net radiation play key role in determining the flux components in all studied ecosystems. It was confirmed that a chronologic scan of the available patterns is needed for a thorough assessment of the performance accuracy of the local models. The external models provided promising results when compared with the locally trained models. This is a very great step forward in estimating CO2 flux components under data scarcity conditions.

Physiological and environmental control on ecosystem water use efficiency in response to drought across the northern hemisphere.

Drought, a natural hydrometeorological phenomenon, has been more frequent and more widespread due to climate change. Water availability strongly regulates the coupling (or trade-off) between carbon uptake via photosynthesis and water loss through transpiration, known as water-use efficiency (WUE). Understanding the effects of drought on WUE across different vegetation types and along the wet to dry gradient is paramount to achieving better understanding of ecosystem functioning in response to climate change. We explored the physiological and environmental control on ecosystem WUE in response to drought using observations for 44 eddy covariance flux sites in the Northern Hemisphere. We quantified the response of WUE to drought and the relative contributions of gross primary production (GPP) and evapotranspiration (ET) to the variations of WUE. We also examined the control of physiological and environmental factors on monthly WUE under different moisture conditions. Cropland had a peak WUE value under moderate drought conditions, while grassland, deciduous broadleaf forest (DBF), evergreen broadleaf forest (EBF), and evergreen needleleaf forest (ENF) had peak WUE under slight drought conditions. WUE was mainly driven by GPP for cropland, grassland, DBF, and ENF but was mainly driven by ET for EBF. Vapor pressure deficit (VPD) and canopy conductance (Gc) were the most important factors regulating WUE. Moreover, WUE had negative responses to air temperature, precipitation, and VPD but had a positive response to Gc and ecosystem respiration. Our findings highlight the different effects of biotic and abiotic factors on WUE among different vegetation types and the important roles of VPD and Gc in controlling ecosystem WUE in response to drought.

Evaluation of a satellite-derived model parameterized by three soil moisture constraints to estimate terrestrial latent heat flux in the Heihe River basin of Northwest China.

Satellite-derived terrestrial latent heat flux (LE) models are useful tools to understand regional surface energy and water cycle processes for terrestrial ecosystems in the Heihe River basin (HRB) of Northwest China. This study developed a satellite-derived hybrid LE model parameterized by three soil moisture (SM) constraints: SM, relative humidity (RH), and diurnal air temperature range (DT); and assessed model performance and sensitivity. We used MODerate Resolution Imaging Spectroradiometer (MODIS) and eddy covariance (EC) data from 12 EC flux tower sites across the HRB. The hybrid model was trained using observed LE over 2012/2013-2014, and validated using observed LE for 2015 and leave-one-out cross-validation. The results show that the three SM constraints schemes exhibited some modeling differences at the flux tower site scale. LE estimation using SM achieved the highest correlation (R2 = 0.87, p < 0.01) and lowest root mean square error (RMSE = 20.1 W/m2) compared to schemes using RH or DT schemes. We then produced regional daily LE maps at 1 km × 1 km across the HRB for 2013-2015. Regional analysis shows that our LE estimates from all three constraint models exhibited large spatial variability and strong seasonal and annual variations, attributed to differences in parameterizing the model water constraints. This study provides data and model based evidence to improve satellite-derived hybrid LE models with regard to water constraints.

Long-Term Spatiotemporal Variations in Soil Moisture in North East China Based on 1-km Resolution Downscaled Passive Microwave Soil Moisture Products.

It is very important to analyze and monitor agricultural drought to obtain high temporal-spatial resolution soil moisture products. To overcome the deficiencies of passive microwave soil moisture products with low resolution, we construct a spatial fusion downscaling model (SFDM) using Moderate Resolution Imaging Spectroradiometer (MODIS) data. To eliminate the inconsistencies in soil depth and time among different microwave soil moisture products (Advanced Microwave Scanning Radiometer on the Earth Observing System (AMSR-E) and its successor (AMSR2) and the Soil Moisture Ocean Salinity (SMOS)), a time series reconstruction of the difference decomposition (TSRDD) method is developed to create long-term multisensor soil moisture datasets. Overall, the downscaled soil moisture (SM) products were consistent with the in situ measurements (R > 0.78) and exhibited a low root mean square error (RMSE < 0.10 m3/m3), which indicates good accuracy throughout the time series. The downscaled SM data at a 1-km spatial resolution were used to analyze the spatiotemporal patterns and monitor abnormal conditions in the soil water content across North East China (NEC) between 2002 and 2018. The results showed that droughts frequently appeared in western North East China and southwest of the Greater Khingan Range, while drought centers appeared in central North East China. Waterlogging commonly appeared in low-terrain areas, such as the Songnen Plain. Seasonal precipitation and temperature exhibited distinct interdecadal characteristics that were closely related to the occurrence of extreme climatic events. Abnormal SM levels were often accompanied by large meteorological and natural disasters (e.g., the droughts of 2008, 2015, and 2018 and the flooding events of 2003 and 2013). The spatial distribution of drought in this region during the growing season shows that the drought-affected area is larger in the west than in the east and that the semiarid boundary extends eastward and southward.

Deep Learning Convolutional Neural Network for the Retrieval of Land Surface Temperature from AMSR2 Data in China.

A convolutional neural network (CNN) algorithm was developed to retrieve the land surface temperature (LST) from Advanced Microwave Scanning Radiometer 2 (AMSR2) data in China. Reference data were selected using the Moderate Resolution Imaging Spectroradiometer (MODIS) LST product to overcome the problem related to the need for synchronous ground observation data. The AMSR2 brightness temperature (TB) data and MODIS surface temperature data were randomly divided into training and test datasets, and a CNN was constructed to simulate passive microwave radiation transmission to invert the surface temperature. The twelve V/H channel combinations (7.3, 10.65, 18.7, 23.8, 36.5, 89 GHz) resulted in the most stable and accurate CNN retrieval model. Vertical polarizations performed better than horizontal polarizations; however, because CNNs rely heavily on large amounts of data, the combination of vertical and horizontal polarizations performed better than a single polarization. The retrievals in different regions indicated that the CNN accuracy was highest over large bare land areas. A comparison of the retrieval results with ground measurement data from meteorological stations yielded R2 = 0.987, RMSE = 2.69 K, and an average relative error of 2.57 K, which indicated that the accuracy of the CNN LST retrieval algorithm was high and the retrieval results can be applied to long-term LST sequence analysis in China.