Data-Driven Anomaly Detection Approach for Time-Series Streaming Data

Recently, wireless sensor networks (WSNs) have been extensively deployed to monitor environments. Sensor nodes are susceptible to fault generation due to hardware and software failures in harsh environments. Anomaly detection for the time-series streaming data of sensor nodes is a challenging but critical fault diagnosis task, particularly in large-scale WSNs. The data-driven approach is becoming essential for the goal of improving the reliability and stability of WSNs. We propose a data-driven anomaly detection approach in this paper, named median filter (MF)-stacked long short-term memory-exponentially weighted moving average (LSTM-EWMA), for time-series status data, including the operating voltage and panel temperature recorded by a sensor node deployed in the field. These status data can be used to diagnose device anomalies. First, a median filter (MF) is introduced as a preprocessor to preprocess obvious anomalies in input data. Then, stacked long short-term memory (LSTM) is employed for prediction. Finally, the exponentially weighted moving average (EWMA) control chart is employed as a detector for recognizing anomalies. We evaluate the proposed approach for the panel temperature and operating voltage of time-series streaming data recorded by wireless node devices deployed in harsh field conditions for environmental monitoring. Extensive experiments were conducted on real time-series status data. The results demonstrate that compared to other approaches, the MF-stacked LSTM-EWMA approach can significantly improve the detection rate (DR) and false rate (FR). The average DR and FR values with the proposed approach are 95.46% and 4.42%, respectively. MF-stacked LSTM-EWMA anomaly detection also achieves a better F2 score than that achieved by other methods. The proposed approach provides valuable insights for anomaly detection in WSNs by detecting anomalies in the time-series status data recorded by wireless sensor nodes.

The weakening relationship between Eurasian spring snow cover and Indian summer monsoon rainfall

Substantial progress has been made in understanding how Eurasian snow cover variabilities affect the Indian summer monsoon, but the snow-monsoon relationship in a warming atmosphere remains controversial. Using long-term observational snow and rainfall data (1967-2015), we identified that the widely recognized inverse relationship of central Eurasian spring snow cover with the Indian summer monsoon rainfall has disappeared since 1990. The apparent loss of this negative correlation is mainly due to the central Eurasian spring snow cover no longer regulating the summer mid-tropospheric temperature over the Iranian Plateau and surroundings, and hence the land-ocean thermal contrast after 1990. A reduced lagged snow-hydrological effect, resulting from a warming-induced decline in spring snow cover, constitutes the possible mechanism for the breakdown of the snow-air temperature connection after 1990. Our results suggest that, in a changing climate, Eurasian spring snow cover may not be a faithful predictor of the Indian summer monsoon rainfall.

Quantifying the effects of climate and anthropogenic change on regional species loss in China

Human-induced environmental and climate change are widely blamed for causing rapid global biodiversity loss, but direct estimation of the proportion of biodiversity lost at local or regional scales are still infrequent. This prevents us from quantifying the main and interactive effects of anthropogenic environmental and climate change on species loss. Here, we demonstrate that the estimated proportion of species loss of 252 key protected vertebrate species at a county level of China during the past half century was 27.2% for all taxa, 47.7% for mammals, 28.8% for amphibians and reptiles and 19.8% for birds. Both human population increase and species richness showed significant positive correlations with species loss of all taxa combined, mammals, birds, and amphibians and reptiles. Temperature increase was positively correlated with all-taxa and bird species loss. Precipitation increase was negatively correlated with species loss of birds. Human population change and species richness showed more significant interactions with the other correlates of species loss. High species richness regions had higher species loss under the drivers of human environmental and climate change than low-richness regions. Consequently, ongoing human environmental and climate changes are expected to perpetuate more negative effects on the survival of key vertebrate species, particularly in high-biodiversity regions.