Search

Abstract Fruit tree identification that is quick and precise lays the groundwork for scientifically evaluating orchard yields and dynamically monitoring planting areas. This study aims to evaluate the applicability of time series Sentinel-1/2 satellite data for fruit tree classification and to provide a new method for accurately extracting fruit tree species. Therefore, the study area selected is the Tarim Basin, the most important fruit-growing region in northwest China. The main focus is on identifying several major fruit tree species in this region. Time series Sentinel-1/2 satellite images acquired from the Google Earth Engine (GEE) platform are used for the study. A multi-scale segmentation approach is applied, and six categories of features including spectral, phenological, texture, polarization, vegetation index, and red edge index features are constructed. A total of forth-four features are extracted and optimized using the Vi feature importance index to determine the best time phase. Based on this, an object-oriented (OO) segmentation combined with the Random Forest (RF) method is used to identify fruit tree species. To find the best method for fruit tree identification, the results are compared with three other widely used traditional machine learning algorithms: Support Vector Machine (SVM), Gradient Boosting Decision Tree (GBDT), and Classification and Regression Tree (CART). The results show that: (1) the object-oriented segmentation method helps to improve the accuracy of fruit tree identification features, and September satellite images provide the best time window for fruit tree identification, with spectral, phenological, and texture features contributing the most to fruit tree species identification. (2) The RF model has higher accuracy in identifying fruit tree species than other machine learning models, with an overall accuracy (OA) and a kappa coefficient (KC) of 94.60% and 93.74% respectively, indicating that the combination of object-oriented segmentation and RF algorithm has great value and potential for fruit tree identification and classification. This method can be applied to large-scale fruit tree remote sensing classification and provides an effective technical means for monitoring fruit tree planting areas using medium-to-high-resolution remote sensing images.

Water scarcity is one of the most significant environmental factors that inhibits photosynthesis and decreases the growth and productivity of plants. Using the deep learning convolutional neural network (CNN) model, this study evaluates the ability of spectroscopy to estimate leaf water content (LWC) in fruit trees. During midday, spectral data were acquired from leaf samples obtained from three distinct varieties of fruit trees, encompassing the spectral range spanning from 350 to 2500 nm. Then, for spectral preprocessing, the fractional order derivative (FOD) and continuous wavelet transform (CWT) algorithms were used to reduce the effects of scattering and noise on the collected spectra. Finally, the CNN model was developed to predict LWC in different fruit trees. The results showed that: (1) The spectra treated with CWT and FOD could improve the spectrum expression ability by improving the correlation between spectra and LWC. The correlation level of FOD treatment was higher than that of CWT treatment. (2) The CNN model was developed using FOD 1.2, and CWT 3 performed better than other traditional machine learning methods, such as RFR, SVR, and PLSR. (3) Further validation using additional samples demonstrated that the CNN model had good stability and quantitative prediction capability for the LWC of fruit trees (R2 > 0.95, root mean square error (RMSE) < 1.773%, and relative percentage difference (RPD) > 4.26). The results may provide an effective way to predict fruit LWC using a CNN-based model.

Soil salinization is one of the most widespread soil degradation processes on Earth, especially in arid and semi-arid areas. The salinized soil in arid to semi-arid Xinjiang Uyghur Autonomous Region in China accounts for 31% of the area of cultivated land, and thus it is pivotal for the sustainable agricultural development of the area to identify reliable and cost-effective methodologies to monitor the spatial and temporal variations in soil salinity. This objective was accomplished over the study area (Keriya River Basin, northwestern China) by adopting technologies that heavily rely on, and integrate information contained in, a readily available suite of remote sensing datasets. The following procedures were conducted: (1) a selective principle component analysis (S-PCA) fusion image was generated using Phased Array Type L-band SAR (PALSAR) backscattering coefficient (σ°) and Landsat Enhanced Thematic Mapper Plus (ETM+) multispectral image of Keriya River Basin; and (2) a support vector machines (SVM) classification method was employed to classify land cover types with a focus on mapping salinized soils; (3) a cross-validation method was adopted to identify the optimum classification parameters, and obtain an optimal SVM classification model; (4) Radarsat-2 (C band) and PALSAR polarimetric images were used to analyze polarimetric backscattering behaviors in relation to the variation in soil salinization; (5) a decision tree (DT) scheme for multi-source optical and polarimetric SAR data integration was proposed to improve the estimation and monitoring accuracies of soil salinization; and (6) detailed field observations and ground truthing were used for validation of the adopted methodology, and quantity and allocation disagreement measures were applied to assess classification outcome. Results showed that the fusion of passive reflective and active microwave remote sensing data provided an effective tool in detecting soil salinization. Overall accuracy of the adopted SVM classifier with optimal parameters for fused image of ETM+ and PALSAR data was 91.25% with a Kappa coefficient of 0.89, which was further improved by the DT data integration and classification method yielding an accuracy of 93.01% with a Kappa coefficient of 0.92 and lower disagreement of quantity and allocation.

Spatio-temporal analysis of crop water requirement and crop irrigation water requirement is crucial to the optimal allocation of water resources and the formulation of irrigation systems. The objective of this study is to understand the spatio-temporal characteristics and influencing factors of the water requirement during the growth period and irrigation water requirement of the main crops in Xinjiang, cotton, spring wheat, winter wheat, and corn. Based on the daily meteorological observation data from 1960 to 2020, the Penman-Monteith formula and the single crop coefficient method were adopted in this study, and Mann-Kendall (TFPW-MK) of Detrended Preset White (TFPW) was used to study the changing characteristics of water requirement of four crops. The temporal and spatial evolution trend of crop water requirement and irrigation water requirement were predicted by rescaled range (R/S) analysis. Using the principle of important covariate feature identification of the random forest model, the importance ranking of meteorological factors and crop water requirement was analyzed, and the causes of changes in crop water requirement were explored. The results show that: 1) the water requirement of major crops in Xinjiang had generally shown a trend of "increase first, then decrease and then increase" for 61 year. The order of crop water demand and irrigation water requirement from large to small was: cotton > corn > winter wheat > spring wheat. In terms of space, there was a spatial distribution of "Southern Xinjiang>Northern Xinjiang, Southeast>Northwest, East>Western". The variation range of water requirement for major crops was: cotton 381.20-991.20 mm (mean 654.94 mm), corn 350.26-924.48 mm (mean 607.98 mm), spring wheat 361.96-709.69 mm (average 464.89 mm), winter wheat 266.47-753.62 mm (average 495.7 0 mm). The range of irrigation water requirement was: cotton 49.49-975.88 mm (average 563.19 mm), corn 52.47-910.85 mm (average 530.18 mm), spring wheat 42.58-701.29 mm (average 409.28 mm), winter wheat 21.94-741.77 mm (average 418.26 mm). Since the middle and late 1980s, irrigation water requirement decreased more than water requirement. 2) According to the TFPW-MK analysis, in the past 61 years, the water requirement of 12 stations mainly distributed in the northern edge of the Tarim Basin, including Shaya and Aksu, and Baekol in the eastern Xinjiang, showed an upward trend. The water requirement of 27 stations in Karamay in Xinjiang and Artux in southern Xinjiang gradually decreased; the rest of the stations fluctuated up and down. 3) In the prediction of future water demand using the R/S method, four crop water demand and irrigation water demand at Tacheng, Toli, Fuyun and Urumqi stations in northern Xinjiang, Baekol in eastern Xinjiang, and Shaya, Wuqia, Tazhong, Qiemo and Kalpin stations in southern Xinjiang will decrease in the future, while spring and winter wheat water demand at Hongliuhe, Baekol and Bayanbulak in eastern Xinjiang will show an increasing trend in the future. 4) During the crop growth period, wind speed and temperature were the most important factors affecting the water requirement of major crops in Xinjiang, while precipitation was the least important factor for the water requirement of major crops in Xinjiang. This research comprehensively provides decision-making and basis for the formulation of high-efficiency agricultural water use and irrigation measures in Xinjiang. [ABSTRACT FROM AUTHOR]

Hyperspectral data provide valuable information for salt content estimation. In this paper, soil samples were collected from the Keriya Oasis, Southern Xinjiang, China. Samples were bagged, brought to the laboratory, air-dried, ground, and sieved using 2 mm size sieve. Soil salt contents were measured and the reflectance spectra were collected using FieldSpec3 in laboratory condition. The continuum removal (CR) reflectance was obtained after smoothing and averaged spectral data conversion of 10 nm interval. A total of 8 spectral slopes at the wavelength between 365-375 nm, 1435-1465 nm, 1855- 1865 nm, 1915-1925 nm, 2085-2095 nm, 2295-2315 nm, 2365-2395 nm and 2465-2475 nm were calculated based on the correlation analysis between soil salt content and its spectrum. Thirty of 40 samples were used for establishing hyperspectral model for estimating soil salt content and the other 10 samples were for the model verification. The multiple linear regression (MLR) and partial least squares regression (PLSR) were used to model and estimate soil salt content. The results showed that, when soil salt content is higher than 2.10 g.kg-1, spectral slope values increase with the increase of salt content. The estimation accuracy of the model based on MLR was higher than the model based on PLSR. The R2 for calibration and validation of the optimum multiple linear regression model were up to 0.834 and 0.664, respectively, and its RMSE values of calibration and validation were 2.9707 and 3.2691, and the RPD value was 2.09, respectively. This spectral slope based model was a supplementary modelling for hyperspectral soil salinity estimation, and can be a basis for future satellite-based hyperspectral monitoring and evaluation of soil salinity. [ABSTRACT FROM AUTHOR]