Search

The accurate estimation of leaf chlorophyll content (LCC) is a significant foundation in assessing litchi photosynthetic activity and possible nutrient status. Hyperspectral remote sensing data have been widely used in agricultural quantitative monitoring research for the non-destructive assessment of LCC. Variable selection approaches are crucial for analyzing high-dimensional datasets due to the high danger of overfitting, time-intensiveness, or substantial computational requirements. In this study, the performance of five machine learning regression algorithms (MLRAs) was investigated based on the hyperspectral fractional order derivative (FOD) reflection of 298 leaves together with the variable combination population analysis (VCPA)-genetic algorithm (GA) hybrid strategy in estimating the LCC of Litchi. The results showed that the correlation coefficient (r) between the 0.8-order derivative spectrum and LCC had the highest correlation coefficients (r = 0.9179, p < 0.01). The VCPA-GA hybrid strategy fully utilizes VCPA and GA while compensating for their limitations based on a large number of variables. Moreover, the model was developed using the selected 14 sensitive bands from 0.8-order hyperspectral reflectance data with the lowest root mean square error in prediction (RMSEP = 5.04 μ g · cm − 2 ). Compared with the five MLRAs, validation results confirmed that the ridge regression (RR) algorithm derived from the 0.2 order was the most effective for estimating the LCC with the coefficient of determination (R2 = 0.88), mean absolute error (MAE = 3.40   μ g · cm − 2 ), root mean square error (RMSE = 4.23   μ g · cm − 2 ), and ratio of performance to inter-quartile distance (RPIQ = 3.59). This study indicates that a hybrid variable selection strategy (VCPA-GA) and MLRAs are very effective in retrieving the LCC through hyperspectral reflectance at the leaf scale. The proposed methods could further provide some scientific basis for the hyperspectral remote sensing band setting of different platforms, such as an unmanned aerial vehicle (UAV) and satellite. [ABSTRACT FROM AUTHOR]

Aerosols are complex compounds that greatly affect the global radiation balance and climate system and even human health; in addition, aerosols are currently a large source of uncertainty in the numerical simulation process. The arid and semi-arid areas have fragile ecosystems with abundant dust but lack related high-accuracy aerosol data. To solve these problems, we use the bagging trees ensemble model, based on 1 km aerosol optical depth (AOD) data and multiple environmental covariates, to produce a monthly advanced-performance, full-coverage, and high-resolution (250 m) AOD product (named FEC AOD, fusing environmental covariates AOD) covering the arid and semi-arid areas. Then, based on the FEC AOD products, we analyzed the spatiotemporal AOD pattern and further discussed the interpretation of environmental covariates to AOD. The results show that the bagging trees ensemble model has a good performance, with its verification R2 values always remaining at 0.90 and the R2 being 0.79 for FEC AOD compared with AERONET AOD product. The high-AOD areas are located in the Taklimakan Desert and on the Loess Plateau, and the low-AOD areas are concentrated in southern Qinghai province. The higher the AOD, the stronger the interannual variability. Interestingly, the AOD reflected a dramatic decrease on the Loess Plateau and an evident increase in the south-eastern Taklimakan Desert, while the southern Qinghai province AODs showed almost no significant change between 2000 and 2019. The annual variation characteristics show that the AOD was largest in spring (0.267±0.200) and smallest in autumn (0.147±0.089); the annual AOD variation pattern showed different features, with two peaks in March and August over Gansu province but only one peak in April in other provinces/autonomous regions. Farmlands and construction lands have high AOD levels compared to other land cover types. Meteorological factors demonstrate the maximum interpretation ability of the AODs on all set temporal scales, followed by the terrain factors, while surface properties have the smallest explanatory abilities; the corresponding average contributions are 77.1 %, 59.1 %, and 50.4 %, respectively. The capability of the environmental covariates to explain the AOD varies seasonally in the following sequence: winter (86.6 %) > autumn (80.8 %) > spring (79.9 %) > summer (72.5 %). In this research, we provide a pathbreaking high spatial resolution (250 m) and long time series (2000–2019) FEC AOD dataset covering arid and semi-arid regions to support atmospheric and related studies in northwest China; the full dataset is available at 10.5281/zenodo.5727119 (Chen et al., 2021b). [ABSTRACT FROM AUTHOR]

Mechanical metamaterials composed of curvilinear elements (MM-CEs) offer better programmability and functionality than their rectilinear counterparts. They thus hold promising potential for diverse applications, such as flexible electronics, impact protection, and deformation control. However, existing research on MM-CEs has primarily focused on specific curve shapes, neglecting the vast potential of the wider curve design space. Based on data-driven methods, this work builds a dataset with a hierarchical data structure, which transforms the infinite and difficult-to-conceptualize curve data into a finite number of potentially researchable curve sub-types. Moreover, methods are developed based on data mining to better understand the broad design space, excavate hidden connections of different curve sub-types and discover new rules for designing MM-CEs. The outcomes of this study offer novel strategies to investigate other structures and metamaterials with complex geometries as well. [ABSTRACT FROM AUTHOR]

Controlling and managing surface source pollution depends on the rapid monitoring of total nitrogen in water. However, the complex factors affecting water quality (plant shading and suspended matter in water) make direct estimation extremely challenging. Considering the spectral response mechanisms of emergent plants, we coupled discrete wavelet transform (DWT) and fractional order discretization (FOD) techniques with three machine learning models (random forest (RF), bagging algorithm (bagging), and eXtreme Gradient Boosting (XGBoost)) to mine this potential spectral information. A total of 567 models were developed, and airborne hyperspectral data processed with various DWT scales and FOD techniques were compared. The effective information in the hyperspectral reflectance data were better emphasized after DWT processing. After DWT processing the original spectrum (OR), its sensitivity to TN in water was maximally improved by 0.22, and the correlation between FOD and TN in water was optimally increased by 0.57. The transformed spectral information enhanced the TN model accuracy, especially for FOD after DWT. For RF, 82% of the model R2 values improved by 0.02~0.72 compared to the model using FOD spectra; 78.8% of the bagging values improved by 0.01~0.53 and 65.0% of the XGBoost values improved by 0.01~0.64. The XGBoost model with DWT coupled with grey relation analysis (GRA) yielded the best estimation accuracy, with the highest precision of R2 = 0.91 for L6. In conclusion, appropriately scaled DWT analysis can substantially improve the accuracy of extracting TN from UAV hyperspectral images. These outcomes may facilitate the further development of accurate water quality monitoring in sophisticated global waters from drone or satellite hyperspectral data. [ABSTRACT FROM AUTHOR]

[Display omitted] • We updated information on soil salinity: soil salinization exacerbated overall. • Spectral information and environmental covariates were necessary but still needed to filter. • The model with environmental covariates improved on performance for soil salinity. • The GBRT model performance was the best among machine learning models. Soil salinization is the main source of global soil degradation. It has impeded progress towards sustainable development goals (SDGs) by threatening 20% of irrigated areas. However, in many data-poor regions, accurate soil salinization information is unavailable. Thus, an updated soil salinity map with high accuracy and resolution is urgently needed to help local governments conduct precise management. In this study, a bootstrap hybrid machine learning framework was developed combine Sentinel-2 data and environmental covariates. The Boruta algorithm was applied to input the spectral information and environmental variables to identify the primary factors influencing soil salinity. By averaging 100 model iterations within a bootstrap framework, the soil salinity mapping outcomes were compared from four machine learning methods (bagging, classification and regression tree, random forest, and gradient boosting regression tree (GBRT)). The results showed that the models driven by spectral information and environmental covariates (strategy II) explained 68∼88% of the variability in soil salinity. The model accuracy of strategy II was improved by 5%-8% over that of the models driven only by spectral information (strategy I). The GBRT yielded the most appropriate averaging performance of the four machine learning approaches within strategy II, with an R2 of 0.88, a root mean square error (RMSE) of 6.33 dS m−1, a ratio of performance to interquartile distance (RPIQ) of 4.66 and model stability (ROB) of 0.44. The bootstrap averaging method was relatively stable and had high accuracy potential. The distribution of soil salinity in the Ebinur Lake region was the result of a combination of natural and human activity influences. The proposed approach provides a soil salinity mapping strategy with a fine resolution (10 m) and high accuracy in data-poor places. It may also aid in the restoration of biodiversity, the decrease in land degradation, and the avoidance of future food output reductions in the future. [ABSTRACT FROM AUTHOR]