Net primary productivity (NPP), as an indicator of ecological functioning, plays an important role in regional and global carbon cycles. Although many studies have estimated the NPP of vegetation on the Qinghai Plateau (QP), the existing NPP datasets over the QP are either of low spatial resolution or limited-duration time-series. These shortcomings restrict our ability to explore the spatial distribution and long-term trends of NPP at a finer scale. To address this gap, we present a new monthly NPP dataset (QP NPP30) at a high spatial resolution (30 m) over the QP for the period 1987-2021. We constructed this dataset using the Carnegie-Ames-Stanford-Approach (CASA) model and multi-source data, including reconstructed normalized difference vegetation index (NDVI) data, reanalysis data, land cover, and other ancillary data. To reconstruct the NDVI, a harmonic regression model based on the Google Earth Engine (GEE) was applied to the NDVI time series data. Statistical analysis of QP NPP30 showed that the NPP in the QP has increased over the past 35 years (0.92 gC/m² /yr ). Furthermore, we found that NPP is concentrated in June, July, and August, accounting for approximately 73% of the annual total. To validate our dataset, we compared it with measured NPP and with the MODIS NPP product (MOD-NPP). Our results demonstrated that QP NPP30 has similar spatial patterns to MOD-NPP but offers richer spatial detail. Specifically, QP NPP30 has a higher accuracy than MOD-NPP, by comparing with the measured data (r = 0.695, RMSE = 132.823 gC/m² /yr for QP NPP30; r = 0.328, RMSE = 158.586 gC/m² /yr for MOD-NPP).

The lack of long-duration, high-frequency grassland classification products limits further understanding of the grasslands’ long-term succession. This study first explored the annual mapping of grassland with fourteen categories at 30 m in Qinghai, China, from 1986 to 2020 based on Google Earth Engine (GEE) and the Integrated Orderly Classification System (IOCSG). Specifically, we proposed an image composite strategy to obtain annual source images for classification, by quarterly compositing multi-sensor and multi-temporal Landsat surface reflectance images. Subsequently, the 35-year area time series of each category was analyzed in terms of trend, degree of change, and succession of each category. The results indicate that the different grasslands of the IOCSG can be effectively differentiated by utilizing the designed feature bands of remote sensing data. Additionally, the proposed annual image composition strategy can not only decrease the invalid pixels but also promote classification accuracy. The grasslands transition analysis from 1986 to 2020 implies the progressive urbanization, warming, and wetting trend in Qinghai. The generated 35-year annual grassland thematic data in Qinghai can serve as an elementary dataset for further regional ecological and climate change studies. The proposed methodology of large-scale grassland classification can also be referenced to other applications like land use/cover mapping and ecological resource monitoring.

Unsupervised change detection(CD) from remotely sensed images is a fundamental challenge when the ground truth for supervised learning is not easily available. Inspired by the visual attention mechanism and multi-level sensation capacity of human vision, we proposed a novel multi-scale analysis framework based on multi-scale visual saliency coarse-to-fine fusion (MVSF) for unsupervised CD in this paper. As a preface of MVSF, we generalized the connotations of scale as four classes in the field of remote sensing (RS) covering the RS process from imaging to image processing, including intrinsic scale, observation scale, analysis scale and modeling scale. In MVSF, superpixels were considered as the primitives for analysing the difference image(DI) obtained by the change vector analysis method. Then, multi-scale saliency maps at the superpixel level were generated according to the global contrast of each superpixel. Finally, a weighted fusion strategy was designed to incorporate multi-scale saliency at a pixel level. The fusion weight for the pixel at each scale is adaptively obtained by considering the heterogeneity of the superpixel it belongs to and the spectral distance between the pixel and the superpixel. The experimental study was conducted on three bi-temporal remotely sensed image pairs, and the effectiveness of the proposed MVSF was verified qualitatively and quantitatively. The results suggest that it is not entirely true that finer scale brings better CD result, and fusing multi-scale superpixel based saliency at a pixel level obtained a higher F1 score in the three experiments. MVSF is capable of maintaining the detailed changed areas while resisting image noise in the final change map. Analysis of the scale factors in MVSF implied that the performance of MVSF is not sensitive to the manually selected scales in the MVSF framework.

In this paper, we propose a deep learning-based model to detect extratropical cyclones (ETCs) of the northern hemisphere, while developing a novel workflow of processing images and generating labels for ETCs. We first labeled the cyclone center by adapting an approach from Bonfanti et al. in 2017 and set up criteria of labeling ETCs of three categories: developing, mature, and declining stages. We then gave a framework of labeling and preprocessing the images in our dataset. Once the images and labels were ready to serve as inputs, an object detection model was built with Single Shot Detector (SSD) and adjusted to fit the format of the dataset. We trained and evaluated our model with our labeled dataset on two settings (binary and multiclass classifications), while keeping a record of the results. We found that the model achieves relatively high performance with detecting ETCs of mature stage (mean Average Precision is 86.64%), and an acceptable result for detecting ETCs of all three categories (mean Average Precision 79.34%). The single-shot detector model can succeed in detecting ETCs of different stages, and it has demonstrated great potential in the future applications of ETC detection in other relevant settings.

This study presents an adaptive superpixel based Markov Random Field (ASP_MRF) model for unsupervised remotely sensed images change detection. Firstly, the difference image is generated by change vector analysis (CVA) and the zero parameter version of the ‘simple linear iterative clustering’ method (SLICO) is applied on the difference image to obtain the superpixel map. Then, the superpixel map is initially labeled as changed and unchanged class by Fuzzy c-means (FCM) clustering method. Thirdly, the region adjacent graph (RAG) is built on the superpixel map to model the spatial constraints between the adjacent superpixels. Specially, the spectral dissimilarity between the adjacent superpixels and the label fuzziness of the neighbored superpixels were incorporated in the RAG. Lastly, The initial labels of the superpixel map are iteratively refined with ASP_MRF to generate the final change map. The experimental results prove that ASP_MRF obtained the most accurate change map and outperformed the results by pixel level MRF and superpixel based MRF, which verifies the effectiveness of ASP_MRF.