[Spatio-temporal Evolution and Prediction of Carbon Storage in Huaibei City Based on InVEST-PLUS Model].

This study aimed to investigate the impact of spatiotemporal changes in land use on ecosystem carbon storage. The study analyzed the spatiotemporal changes in carbon storage in the study area based on land use data from five periods (1985, 1995, 2005, 2015, and 2020) using the InVEST model. The PLUS model was used to predict land use changes in the study area under four different scenarios (natural development, farmland protection, ecological protection, and double protection of farmland and ecology) in 2035, and the ecosystem carbon storage under different scenarios was estimated. The results of the study indicated that the farmland in the area under investigation had been decreasing consistently from 1985 to 2020, with a more rapid rate of change observed between 2015 and 2020. During this period, the overall dynamic attitude towards land use reached 34.62 %. Additionally, the carbon storage in the area showed a decreasing trend over the years, with a decrease of 1.55×105 t from 1985 to 2020. Between 2005 and 2015, the carbon storage showed a decrease of 1.22×105 t, with an average annual decrease of 1.22×104 t. The areas with higher carbon storage were located in the eastern part of the study area, whereas areas with lower carbon storage were found in the central and northwestern parts. Although the proportion of carbon storage in farmland decreased from 66.89 % to 57.73 %, farmland remained the most important carbon pool in the study area. The conversion of other land use types to grassland and forestland was advantageous for increasing ecosystem carbon storage. Finally, the study projected that by 2035, the carbon storage in the natural development scenario, the farmland protection scenario, the ecological protection scenario, and the dual protection scenario would be 81.77×105, 82.45×105, 82.82×105, and 82.51×105 t, respectively.

[Spatial Prediction Modeling for Soil pH Based on Multiscale Geographical Weighted Regression(MGWR) and Its Influencing Factors].

Anhui, Henan, Jiangsu, and Shandong provinces were selected as the study area. A total of 599 soil samples and nine environmental factors of soil pH were collected. The spatial distribution of soil pH was modeled based on multi-scale geographically weighted regression(MGWR), mixed geographically weighted regression(Mixed GWR), geographically weighted regression(GWR), and multiple linear regression(MLR) models. Then, the spatial difference in the effect of environmental factors on soil pH was revealed using MGWR and quantile regression models. The results showed that:① soil pH showed significant global and local spatial autocorrelation at different spatial distances, and the clustering characteristics were obvious. ② The MGWR model was the best among the four models, and the Radj2 of MGWR, Mixed GWR, GWR, and MLR were 0.64, 0.62, 0.59, and 0.48, respectively. The residual of MGWR had the strongest independent distribution and the weakest spatial autocorrelation with a global Moran's I of 0.07. ③ Three types of GWR predictions showed that the spatial distribution of soil pH decreased gradually from north to south in the study area, with the highest in northern Henan and the lowest in southern Anhui. ④ MGWR modeling results showed that there was strong spatial heterogeneity of mean annual precipitation(MAP), multi-resolution valley bottom flatness(MRVBF), and elevation affecting soil pH. MAP had a stronger effect on soil pH in northern Jiangsu and most parts of Shandong. The positive effect of MRVBF on soil pH was stronger in northern Jiangsu and western Shandong. The negative effect of elevation on soil pH was stronger in northern and central Jiangsu. ⑤ The quantile regression analysis showed that the mean annual precipitation had a significant negative effect on soil pH at different quantile levels of soil pH, and influence intensity decreased with the increase in pH quantile level. MRVBF had a significant negative effect on soil pH at a low quantile level(θ=0.1 to 0.4) but had no significant effect on soil pH at a high quantile level(θ=0.5 to 0.9). These results can provide an important reference for mapping soil properties and analyzing its influence factors based on the MGWR model in large regions.

Improved multivariate modeling for soil organic matter content estimation using hyperspectral indexes and characteristic bands.

Soil organic matter (SOM) is a key index of soil fertility. Calculating spectral index and screening characteristic band reduce redundancy information of hyperspectral data, and improve the accuracy of SOM prediction. This study aimed to compare the improvement of model accuracy by spectral index and characteristic band. This study collected 178 samples of topsoil (0-20 cm) in the central plain of Jiangsu, East China. Firstly, visible and near-infrared (VNIR, 350-2500 nm) reflectance spectra were measured using ASD FieldSpec 4 Std-Res spectral radiometer in the laboratory, and inverse-log reflectance (LR), continuum removal (CR), first-order derivative reflectance (FDR) were applied to transform the original reflectance (R). Secondly, optimal spectral indexes (including deviation of arch, difference index, ratio index, and normalized difference index) were calculated from each type of VNIR spectra. Characteristic bands were selected from each type of spectra by the competitive adaptive reweighted sampling (CARS) algorithm, respectively. Thirdly, SOM prediction models were established based on random forest (RF), support vector regression (SVR), deep neural networks (DNN) and partial least squares regression (PLSR) methods using optimal spectral indexes, denoted here as SI-based models. Meanwhile, SOM prediction models were established using characteristic wavelengths, denoted here as CARS-based models. Finally, this research compared and assessed accuracy of SI-based models and CARS-based models, and selected optimal model. Results showed: (1) The correlation between optimal spectral indexes and SOM was enhanced, with absolute value of correlation coefficient between 0.66 and 0.83. The SI-based models predicted SOM content accurately, with the coefficient of determination (R2) and root mean square error (RMSE) values ranging from 0.80 to 0.87, 2.40 g/kg to 2.88 g/kg in validation sets, and relative percent deviation (RPD) value between 2.14 and 2.52. (2) The accuracy of CARS-based models differed with models and spectral transformations. For all spectral transformations, PLSR and SVR combined with CARS displayed the best prediction (R2 and RMSE values ranged from 0.87 to 0.92, 1.91 g/kg to 2.56 g/kg in validation sets, and RPD value ranged from 2.41 to 3.23). For FDR and CR spectra, DNN and RF models achieved more accuracy (R2 and RMSE values ranged from 0.69 to 0.91, 1.90 g/kg to 3.57 g/kg in validation sets, and RPD value ranged from 1.73 to 3.25) than LR and R spectra (R2 and RMSE values from 0.20 to 0.35, 5.08 g/kg to 6.44 g/kg in validation sets, and RPD value ranged from 0.96 to 1.21). (3) Overall, the accuracy of SI-based models was slightly lower than that of CARS-based models. But spectral index had a good adaptability to the models, and each SI-based model displayed the similar accuracy. For different spectra, the accuracy of CARS-based model differed from modeling methods. (4) The optimal CARS-based model was model CARS-CR-SVR (R2 and RMSE: 0.92 and 1.91 g/kg in validation set, RPD: 3.23). The optimal SI-based model was model SI3-SVR (R2 and RMSE: 0.87 and 2.40 g/kg in validation set, RPD: 2.57) and model SI-SVR (R2 and RMSE: 0.84 and 2.63 g/kg in validation set, RPD: 2.35).

[Assessing soil pH in Anhui Province based on different features mining methods combined with generalized boosted regression models]. / 基于不同特征挖掘方法结合广义提升回归模型估测安徽省土壤pH.

We explored the application of different feature mining methods combined with genera-lized boosted regression models in digital soil mapping. Environmental covariates were selected by two feature selection methods i.e., recursive feature elimination and selection by filtering. Using the original environmental covariates and the selected optimal variable combination as independent varia-bles, soil pH prediction model of Anhui Province was established and mapped based on the genera-lized boosted regression model and random forest model. The results showed that both kinds of feature mining methods could effectively improve the accuracy of soil pH prediction by generalized boosted regression models and random forest model, and could reduce dimensionality. Compared with the random forest model, the prediction accuracy of the validation set of the generalized boosted regression model was slightly lower. In the training set, the accuracy of the generalized boosted regression models was much higher than that of the random forest model, with higher interpretation and better overall effect. The main parameters of the random forest model, ntree and mtry, had limi-ted effect on the model. Different parameters and their combination could affect the prediction accuracy of the generalized boosted regression models, and thus should be tuned before modeling. The results of spatial mapping showed that soil pH in Anhui Province showed a pattern of "south acid and north alkali".

Retrieval and Mapping of Soil Texture Based on Land Surface Diurnal Temperature Range Data from MODIS.

Numerous studies have investigated the direct retrieval of soil properties, including soil texture, using remotely sensed images. However, few have considered how soil properties influence dynamic changes in remote images or how soil processes affect the characteristics of the spectrum. This study investigated a new method for mapping regional soil texture based on the hypothesis that the rate of change of land surface temperature is related to soil texture, given the assumption of similar starting soil moisture conditions. The study area was a typical flat area in the Yangtze-Huai River Plain, East China. We used the widely available land surface temperature product of MODIS as the main data source. We analyzed the relationships between the content of different particle soil size fractions at the soil surface and land surface day temperature, night temperature and diurnal temperature range (DTR) during three selected time periods. These periods occurred after rainfalls and between the previous harvest and the subsequent autumn sowing in 2004, 2007 and 2008. Then, linear regression models were developed between the land surface DTR and sand (> 0.05 mm), clay (< 0.001 mm) and physical clay (< 0.01 mm) contents. The models for each day were used to estimate soil texture. The spatial distribution of soil texture from the studied area was mapped based on the model with the minimum RMSE. A validation dataset produced error estimates for the predicted maps of sand, clay and physical clay, expressed as RMSE of 10.69%, 4.57%, and 12.99%, respectively. The absolute error of the predictions is largely influenced by variations in land cover. Additionally, the maps produced by the models illustrate the natural spatial continuity of soil texture. This study demonstrates the potential for digitally mapping regional soil texture variations in flat areas using readily available MODIS data.