Accurate forecasting of photovoltaic (PV) power is essential for grid scheduling and energy management. In recent years, deep learning technology has made significant progress in time-series forecasting, offering new solutions for PV power forecasting. This study provides a systematic review of deep learning models for PV power forecasting, concentrating on comparisons of the features, advantages, and limitations of different model architectures. First, we analyze the commonly used datasets for PV power forecasting. Additionally, we provide an overview of mainstream deep learning model architectures, including multilayer perceptron (MLP), recurrent neural networks (RNN), convolutional neural networks (CNN), and graph neural networks (GNN), and explain their fundamental principles and technical features. Moreover, we systematically organize the research progress of deep learning models based on different architectures for PV power forecasting. This study indicates that different deep learning model architectures have their own advantages in PV power forecasting. MLP models have strong nonlinear fitting capabilities, RNN models can capture long-term dependencies, CNN models can automatically extract local features, and GNN models have unique advantages for modeling spatiotemporal characteristics. This manuscript provides a comprehensive research survey for PV power forecasting using deep learning models, helping researchers and practitioners to gain a deeper understanding of the current applications, challenges, and opportunities of deep learning technology in this area.

MapReduce has been widely used in Hadoop for parallel processing larger-scale data for the last decade. However, remote-sensing (RS) algorithms based on the programming model are trapped in dense disk I/O operations and unconstrained network communication, and thus inappropriate for timely processing and analyzing massive, heterogeneous RS data. In this paper, a novel in-memory computing framework called Apache Spark (Spark) is introduced. Through its merits of transferring transformation to in-memory datasets of Spark, the shortages are eliminated. To facilitate implementation and assure high performance of Spark-based algorithms in a complex cloud computing environment, a strip-oriented parallel programming model is proposed. By incorporating strips of RS data with resilient distributed datasets (RDDs) of Spark, all-level parallel RS algorithms can be easily expressed with coarse-grained transformation primitives and BitTorrent-enabled broadcast variables. Additionally, a generic image partition method for Spark-based RS algorithms to efficiently generate differentiable key/value strips from a Hadoop distributed file system (HDFS) is implemented for concealing the heterogeneousness of RS data. Data-intensive multitasking algorithms and iteration-intensive algorithms were evaluated on a Hadoop yet another resource negotiator (YARN) platform. Experiments indicated that our Spark-based parallel algorithms are of great efficiency, a multitasking algorithm took less than 4 h to process more than half a terabyte of RS data on a small YARN cluster, and 9*9 convolution operations against a 909-MB image took less than 260 s. Further, the efficiency of iteration-intensive algorithms is insensitive to image size.

In current upscaling of in situ surface soil moisture practices, commonly used novel statistical or machine learning-based regression models combined with remote sensing data show some advantages in accurately capturing the satellite footprint scale of specific local or regional surface soil moisture. However, the performance of most models is largely determined by the size of the training data and the limited generalization ability to accomplish correlation extraction in regression models, which are unsuitable for larger scale practices. In this paper, a deep learning model was proposed to estimate soil moisture on a national scale. The deep learning model has the advantage of representing nonlinearities and modeling complex relationships from large-scale data. To illustrate the deep learning model for soil moisture estimation, the croplands of China were selected as the study area, and four years of Visible Infrared Imaging Radiometer Suite (VIIRS) raw data records (RDR) were used as input parameters, then the models were trained and soil moisture estimates were obtained. Results demonstrate that the estimated models captured the complex relationship between the remote sensing variables and in situ surface soil moisture with an adjusted coefficient of determination of ${\overline{\mathrm{R}}}^2$ = 0.9875 and a root mean square error (RMSE) of 0.0084 in China. These results were more accurate than the Soil Moisture Active Passive (SMAP) active radar soil moisture products and the Global Land data assimilation system (GLDAS) 0–10 cm depth soil moisture data. Our study suggests that deep learning model have potential for operational applications of upscaling in situ surface soil moisture data at the national scale.

Mapping rice cropping systems is important for grain yield prediction and food security assessments. Both single- and double-season rice are the dominant rice systems in central China. However, because of increasing labor shortages and high costs, there has been a gradual decline in double-season rice. Ratoon rice (RR) has been proposed as an alternative system that balances the productivity, cost, and labor requirements of rice cultivation. RR has been expanding in central China, encouraged by the improved cultivars, machinery, and favorable policies. However, to our knowledge, the distribution of RR has not been mapped with remote sensing techniques. This study developed a phenology-based algorithm to map RR at a 10 m resolution in Hubei Province, Central China, using dense time stacks of Sentinel-2 images (cloud cover <80%) in 2018. The key in differentiating RR from the other rice cropping systems is through the timing of maturity. We proposed to use two contrast vegetation indices to identify RR fields. The newly-developed yellowness index (YI) calculated with the reflectance of blue, green, and red bands was used to detect the ripening phase, and the enhanced vegetation index (EVI) was used to detect the green-up of the second-season crop to eliminate the misclassification caused by stubbles left in the field. The RR map demonstrated that RR was mainly distributed in the low alluvial plains of central and southern Hubei Province. The total planting area of RR in 2018 was 2225.4 km², accounting for 10.03% of the total area of paddy rice fields. The overall accuracy of RR, non-RR rice fields, and non-rice land cover types was 0.76. The adjusted overall accuracy for RR and non-RR was 0.91, indicating that the proposed YI and the phenology-based algorithm could accurately identify RR fields from the paddy rice fields.

The vegetation supply water index (VSWI = NDVI/LST) is an effective metric estimating soil moisture in areas with moderate to dense vegetation cover. However, the normalized difference vegetation index (NDVI) exhibits a long water stress lag and the land surface temperature (LST), sensitive to water stress, does not contribute considerably to surface soil moisture monitoring due to the constraints of the mathematical characteristics of VSWI: LST influences VSWI less when LST value is sufficiently high. This paper mathematically analyzes the characteristics of VSWI and proposes a new operational dryness index (surface water content temperature index, SWCTI) for the assessment of surface soil moisture status. SWCTI uses the surface water content index (SWCI), which provides a more accurate estimation of surface soil moisture than that of NDVI, as the numerator and the modified surface temperature, which has a greater influence on SWCTI than that of LST, as the denominator. The validation work includes comparison of SWCTI with in situ soil moisture and other remote sensing indices. The results show SWCTI demonstrates the highest correlation with in situ soil moisture; the highest correlation R = 0.801 is found between SWCTI and the 0–5 cm soil moisture in a sandy loam. SWCTI is a functional and effective method that has a great potential in surface soil moisture monitoring.

Geospatial big data analysis (GBDA) is extremely significant for time-constraint applications such as disaster response. However, the time-constraint analysis is not yet a trivial task in the cloud computing environment. Spatial query processing (SQP) is typical computation-intensive and indispensable for GBDA, and the spatial range query, join query, and the nearest neighbor query algorithms are not scalable without using MapReduce-liked frameworks. Parallel SQP algorithms (PSQPAs) are trapped in screw-processing, which is a known issue in Geoscience. To satisfy time-constrained GBDA, we propose an elastic SQP approach in this paper. First, Spark is used to implement PSQPAs. Second, Kubernetes-managed Core Operation System (CoreOS) clusters provide self-healing Docker containers for running Spark clusters in the cloud. Spark-based PSQPAs are submitted to Docker containers, where Spark master instances reside. Finally, the horizontal pod auto-scaler (HPA) would scale-out and scale-in Docker containers for supporting on-demand computing resources. Combined with an auto-scaling group of virtual instances, HPA helps to find each of the five nearest neighbors for 46,139,532 query objects from 834,158 spatial data objects in less than 300 s. The experiments conducted on an OpenStack cloud demonstrate that auto-scaling containers can satisfy time-constraint GBDA in clouds.