Gap Filling for Historical Landsat NDVI Time Series by Integrating Climate Data

Anomaly Detection and Repairing for Improving Air Quality Monitoring

Clean air in cities improves our health and overall quality of life and helps fight climate change and preserve our environment. High-resolution measures of pollutants' concentrations can support the identification of urban areas with poor air quality and raise citizens' awareness while encouraging more sustainable behaviors. Recent advances in Internet of Things (IoT) technology have led to extensive use of low-cost air quality sensors for hyper-local air quality monitoring. As a result, public administrations and citizens increasingly rely on information obtained from sensors to make decisions in their daily lives and mitigate pollution effects. Unfortunately, in most sensing applications, sensors are known to be error-prone. Thanks to Artificial Intelligence (AI) technologies, it is possible to devise computationally efficient methods that can automatically pinpoint anomalies in those data streams in real time. In order to enhance the reliability of air quality sensing applications, we believe that it is highly important to set up a data-cleaning process. In this work, we propose AIrSense, a novel AI-based framework for obtaining reliable pollutant concentrations from raw data collected by a network of low-cost sensors. It enacts an anomaly detection and repairing procedure on raw measurements before applying the calibration model, which converts raw measurements to concentration measurements of gasses. There are very few studies of anomaly detection in raw air quality sensor data (millivolts). Our approach is the first that proposes to detect and repair anomalies in raw data before they are calibrated by considering the temporal sequence of the measurements and the correlations between different sensor features. If at least some previous measurements are available and not anomalous, it trains a model and uses the prediction to repair the observations; otherwise, it exploits the previous observation. Firstly, a majority voting system based on three different algorithms detects anomalies in raw data. Then, anomalies are repaired to avoid missing values in the measurement time series. In the end, the calibration model provides the pollutant concentrations. Experiments conducted on a real dataset of 12,000 observations produced by 12 low-cost sensors demonstrated the importance of the data-cleaning process in improving calibration algorithms' performances.

Temporal and Spatial Changes in Vegetation Ecological Quality and Driving Mechanism in Kökyar Project Area from 2000 to 2021

The “Kökyar Greening Project” in the suburb of Aksu, Xinjiang, is a model of large-area artificial afforestation in an environment of drought and water scarcity. As an important part of the “3-North Shelter Forest Program”, it plays an important role in promoting the economic development and the environmentally friendly construction of Aksu and even of the whole Xinjiang region. Based on multisource remote-sensing data and meteorological observation data, this study explored the temporal and spatial changes in the vegetation parameters (FVC, NPP, and VEQI) and the ecological parameters (RSEI and LULC) in the Kökyar Project Area from 2000 to 2021. Based on the Theil–Sen median and TSS-RESTREND, this study investigated the path of mutual influence among the FVC, NPP, VEQI, and RSEI, as well as their responses to climate change and human activities. The results show that: (1) from 2000 to 2021, the FVC, NPP, VEQI, and RSEI in the Kökyar Project Area showed a significant upward trend and showed the distribution characteristics of “high in the south and low in the north”. (2) Over the past 22 years, the RSEI has shown a significant increase with the FVC, NPP and VEQI (p < 0.001), indicating that the “Kökyar Greening Project” has achieved significant ecological benefits. (3) The changes in the vegetation parameters and RSEI in the Kökyar Project Area were dominated by human activities. (4) The Kökyar Project Area has caused great changes to the ecosystem pattern of the region, and the vegetation parameters and RSEI in the Kökyar Project Area have increased, mainly in the form of cropland and grassland expansion over the past 22 years.

An Open Data Approach for Estimating Vegetation Gross Primary Production at Fine Spatial Resolution

Accurate simulations of the spatial and temporal changes in vegetation gross primary production (GPP) play an important role in ecological studies. Previous studies highlighted large uncertainties in GPP datasets based on satellite data with coarse spatial resolutions (>500 m), and implied the need to produce high-spatial-resolution datasets. However, estimating fine spatial resolution GPP is time-consuming and requires an enormous amount of computing storage space. In this study, based on the Eddy Covariance-Light Use Efficiency (EC-LUE) model, we used Google Earth Engine (GEE) to develop a web application (EC-LUE APP) to generate 30-m-spatial-resolution GPP estimates within a region of interest. We examined the accuracy of the GPP estimates produced by the APP and compared them with observed GPP at 193 global eddy covariance sites. The results showed the good performance of the EC-LUE APP in reproducing the spatial and temporal variations in the GPP. The fine-spatial-resolution GPP product (GPPL) explained 64% of the GPP variations and had fewer uncertainties (root mean square error = 2.34 g C m−2 d−1) and bias (−0.09 g C m−2 d−1) than the coarse-spatial-resolution GPP products. In particular, the GPPL significantly improved the GPP estimations for cropland and dryland ecosystems. With this APP, users can easily obtain 30-m-spatial-resolution GPP at any given location and for any given year since 1984.

Detection of Tree Decline (Pinus pinaster Aiton) in European Forests Using Sentinel-2 Data

Moderate-resolution satellite imagery is essential to detect conifer tree decline on a regional scale and address the threat caused by pinewood nematode (PWN), (Bursaphelenchus xylophilus. This is a quarantine organism responsible for pine wilt disease (PWD), which has caused substantial ecological and economic losses in the maritime pine (Pinus pinaster) forests of Portugal. This study describes the first instance of a pre-operational algorithm applied to Sentinel-2 imagery to detect PWD-compatible decline in maritime pine. The Random Forest model relied on a pre-wilting and an in-season image, calibrated with data from a 24-month long field campaign enhanced with Worldview-3 data and the analysis of biological samples (hyperspectral reflectance, pigment quantification in needles, and PWN identification). Independent validation results attested to the good performance of the model with an overall accuracy of 95%, particularly when decline affects more than 30% of the 100 m2 pixel of Sentinel-2. Spectral angle mapper applied to hyperspectral measurements suggested that PWN infection cannot be separated from other drivers of decline in the visible-near infrared domain. Our algorithm can be employed to detect regional decline trends and inform subsequent aerial and field surveys, to further investigate decline hotspots.

Seasonal Variation of Vegetation and Its Spatiotemporal Response to Climatic Factors in the Qilian Mountains, China

The purpose of this study is to reveal the seasonal difference in vegetation variation and its seasonal response to climate factors in the Qilian Mountains (QM) under the background of global warming. Based on the MOD13 A2 normalized difference vegetation index (NDVI) data and meteorological data, this study analyzed the spatiotemporal dynamics and stability of vegetation in different seasons by using the mean value method, trend analysis and stability analysis method, and discussed their seasonal responses to climatic factors based on the correlation analysis method. The results show that the vegetation cover in the QM experienced a significant upward trend in the past 21 years, but there were obvious spatial differences in vegetation change in different seasons. The growth rate of vegetation in summer was the fastest, and summer vegetation provided the most significant contribution to the growing season vegetation. The order of vegetation stability in the QM among the seasons was growing season > summer > spring > autumn. The vegetation change was obviously affected by temperature in spring, while it was mainly controlled by precipitation in the growing season and summer. The response of vegetation to climatic factors was not significant in autumn. Our results can provide important data support for ecological protection in the QM and socioeconomic development in the Hexi Corridor.

Estimating Evapotranspiration over Heterogeneous Surface with Sentinel-2 and Sentinel-3 Data: A Case Study in Heihe River Basin

Evapotranspiration (ET) is an important part of surface–atmosphere interactions, connecting the transfer of matter and energy. Land surface heterogeneity is a natural attribute of the Earth’s surface and is an inevitable problem in calculating ET with coarse resolution remote sensing data, which results in significant error in the ET estimation. This study aims to explore the effect and applicability of the evaporative fraction and area fraction (EFAF) method for correcting 1 km coarse resolution ET. In this study we use the input parameter upscaling (IPUS) algorithm to estimate energy fluxes and the EFAF method to correct ET estimates. Five ground stations in the midstream and downstream regions of the Heihe River Basin (HRB) were used to validate the latent heat flux (LE) calculated by the IPUS algorithm and EFAF method. The evaluation results show that the performance of the EFAF method is superior to that of the IPUS algorithm, with the coefficient of determination (R2) increasing, the root mean square error (RMSE) decreasing, and the mean bias error (MBE) decreasing by 17 W/m2 on average. In general, the EFAF method is suitable for correcting the deviation in LE estimated based on Sentinel data caused by land surface heterogeneity and can be applied to obtain accurate estimates of ET.