The extraction and classification of crops is the core issue of agricultural remote sensing. The precise classification of crop types is of great significance to the monitoring and evaluation of crops planting area, growth, and yield. Based on the Google Earth Engine and Google Colab cloud platform, this study takes the typical agricultural oasis area of Xiangride Town, Qinghai Province, as an example. It compares traditional machine learning (random forest, RF), object-oriented classification (object-oriented, OO), and deep neural networks (DNN), which proposes a random forest combined with deep neural network (RF+DNN) classification framework. In this study, the spatial characteristics of band information, vegetation index, and polarization of main crops in the study area were constructed using Sentinel-1 and Sentinel-2 data. The temporal characteristics of crops phenology and growth state were analyzed using the curve curvature method, and the data were screened in time and space. By comparing and analyzing the accuracy of the four classification methods, the advantages of RF+DNN model and its application value in crops classification were illustrated. The results showed that for the crops in the study area during the period of good growth and development, a better crop classification result could be obtained using RF+DNN classification method, whose model accuracy, training, and predict time spent were better than that of using DNN alone. The overall accuracy and Kappa coefficient of classification were 0.98 and 0.97, respectively. It is also higher than the classification accuracy of random forest (OA = 0.87, Kappa = 0.82), object oriented (OA = 0.78, Kappa = 0.70) and deep neural network (OA = 0.93, Kappa = 0.90). The scalable and simple classification method proposed in this paper gives full play to the advantages of cloud platform in data and operation, and the traditional machine learning combined with deep learning can effectively improve the classification accuracy. Timely and accurate extraction of crop types at different spatial and temporal scales is of great significance for crops pattern change, crops yield estimation, and crops safety warning.

Understanding heavy metal behavior in arid saline soils is critical for phytoremediation in degraded lands. This study investigated metal distribution and plant enrichment in the Tarim Basin using 323 soil and 55 plant samples (Populus euphratica, Tamarix ramosissima, cotton, jujube). Analyses included redundancy analysis (RDA) and bioconcentration factor (BCF) assessments. Key findings reveal that elevated salinity (total salts, TS > 200 g/kg) and alkalinity (pH > 8.5) immobilized As, Cd, Cu, and Zn. Precipitation and competitive leaching reduced metal mobility by 42–68%. Plant enrichment strategies diverged significantly: P. euphratica hyperaccumulated Cd (BCF = 1.59) and Zn (BCF = 2.41), while T. ramosissima accumulated As and Pb (BCF > 0.05). Conversely, cotton posed Hg transfer risks (BCF = 2.15), and jujube approached Cd safety thresholds in phosphorus-rich soils. RDA indicated that pH and total salinity (TS) jointly suppressed metal bioavailability, explaining 57.6% of variance. Total phosphorus (TP) and soil organic carbon (SOC) enhanced metal availability (36.8% variance), with notable TP-Cd synergy (Pearson’s r = 0.42). We propose a dual-threshold management framework: (1) leveraging salinity–alkalinity suppression (TS > 200 g/kg + pH > 8.5) for natural immobilization; and (2) implementing TP control (TP > 0.8 g/kg) to mitigate crop Cd risks. P. euphratica demonstrates targeted phytoremediation potential for degraded saline agricultural systems. This framework guides practical management by spatially delineating zones for natural immobilization versus targeted remediation (e.g., P. euphratica planting in Cd/Zn hotspots) and implementing phosphorus control in high-risk croplands.