Optimize the Coverage Probability of Prediction Interval for Anomaly Detection of Sensor-Based Monitoring Series

Pang, Jingyue; Liu, Datong; Yu, Peng; Peng, Xiyuan

doi:10.3390/s18040967

Cited by 29 publications

(13 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The precision, was quantified with the Prediction Interval Coverage Probability (PICP) and the Mean Prediction Interval Width (MPIW) (Pang et al, 2018) were also computed. The MPIW measures the average width between the upper (u(D i ))…”

Section: Forecast Skill Assessmentmentioning

confidence: 99%

Forecasting Vegetation Condition with a Bayesian Auto-regressive Distributed Lags (BARDL) Model

Salakpi

Hurley

Muthoka

et al. 2021

Preprint

View full text Add to dashboard Cite

Abstract. Droughts form a large part of climate/weather-related disasters reported globally. In Africa, pastoralists living in the Arid and Semi-Arid Lands (ASALs) are the worse affected. Prolonged dry spells that cause vegetation stress in these regions have resulted in the loss of income and livelihoods. To curb this, global initiatives like the Paris Agreement and the United Nations recognised the need to establish Early Warning Systems (EWS) to save lives and livelihoods. Existing EWS use a combination of Satellite Earth Observation (EO) based biophysical indicators like the Vegetation Condition Index (VCI) and socio-economic factors to measure and monitor droughts. Most of these EWS rely on expert knowledge in estimating upcoming drought conditions without using forecast models. Recent research has shown that the use of robust algorithms like Auto-Regression, Gaussian Processes and Artificial Neural Networks can provide very skilled models for forecasting vegetation condition at short to medium range lead times. However, to enable preparedness for early action, forecasts with a longer lead time are needed. The objective of this research work is to develop models that forecast vegetation conditions at longer lead times on the premise that vegetation condition is controlled by factors like precipitation and soil moisture. To achieve this, we used a Bayesian Auto-Regressive Distributed Lag (BARDL) modelling approach which enabled us to factor in lagged information from Precipitation and Soil moisture levels into our VCI forecast model. The results showed a ∼2-week gain in the forecast range compared to the univariate AR model used as a baseline. The R2 scores for the Bayesian ARDL model were 0.94, 0.85 and 0.74, compared to the AR model's R2 of 0.88, 0.77 and 0.65 for 6, 8 and 10 weeks lead time respectively.

show abstract

Section: Forecast Skill Assessmentmentioning

confidence: 99%

Forecasting Vegetation Condition with a Bayesian Auto-regressive Distributed Lags (BARDL) Model

Salakpi

Hurley

Muthoka

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The forecast uncertainties were analysed with the Mean Prediction Interval Width (MPIW) and the Prediction Interval Coverage Probability (PICP) (Pang et al, 2018). The PICP computes the percentage of time the observed variable falls within a chosen prediction interval.…”

Section: Forecasting and Model Evaluationmentioning

confidence: 99%

A Dynamic Hierarchical Bayesian Approach for Forecasting Vegetation Condition

Salakpi

Hurley

Muthoka

et al. 2021

Preprint

View full text Add to dashboard Cite

Abstract. Agricultural drought, which occurs due to a significant reduction in the moisture required for vegetation growth, is the most complex amongst all drought categories. The onset of agriculture drought is slow and can occur over vast areas with varying spatial effects, differing in areas with a particular vegetation land cover or specific agro-ecological sub-regions. These spatial variations imply that monitoring and forecasting agricultural drought require complex models that consider the spatial variations in a given region of interest. Hierarchical Bayesian Models are suited for modelling such complex systems. Using partially pooled data with sub-groups that characterise spatial differences, these models can capture the sub-group variation while allowing flexibility and information sharing between these sub-groups. This paper's objective was to improve the accuracy and precision of agricultural drought forecast in spatially diverse regions with a Hierarchical Bayesian Model. Results showed that the Hierarchical Bayesian Model was better at capturing the variability for the different agro-ecological zones and vegetation land covers compared to a regular Bayesian Auto-Regression Distributed Lags model. The forecasted vegetation condition and associated drought probabilities were more accurate and precise with the Hierarchical Bayesian Model at 4 to 10 weeks lead times. Forecasts from the hierarchical model exhibited higher hit rates with a low probability of false alarms for drought events in semi-arid and arid zones. The Hierarchical Bayesian Model also showed good transferable forecast skills over counties not included in the training data.

show abstract

“…In contrast, prediction-based algorithms primarily detect anomalies by comparing the measured data with the output data predicted by models. Prediction-based algorithms rely on pre-trained models, require no a priori knowledge, are independent of labels, and can detect anomalies in real time [12,13]; as a result, they are more applicable to anomaly detection compared to the aforementioned algorithms. Hence, a prediction-based algorithm is employed in this study to detect abnormal storage battery conditions.…”

Section: Related Workmentioning

confidence: 99%

Detection of Voltage Anomalies in Spacecraft Storage Batteries Based on a Deep Belief Network

Zhang

Liu

2019

Sensors

View full text Add to dashboard Cite

For a spacecraft, its power system is vital to its normal operation and capacity to complete flight missions. The storage battery is an essential component of a power system. As a spacecraft spends more time in orbit and its storage battery undergoes charge/discharge cycles, the performance of its storage battery will gradually decline, resulting in abnormal multivariate correlations between the various parameters of the storage battery system. When these anomalies reach a certain level, battery failure will occur. Therefore, the detection of spacecraft storage battery anomalies in a timely and accurate fashion is of great importance to the in-orbit operation, maintenance and management of a spacecraft. Thus, in this study, based on storage battery-related telemetry parameter data (including charge/discharge currents, voltages, temperatures and times) downloaded from an in-orbit satellite, a voltage anomaly detection algorithm for spacecraft storage batteries based on a deep belief network (DBN) is proposed. By establishing a neural network (NN) model depicting the correlations between each of the variables of temperature, current, pressure and charge/discharge times and voltage, this algorithm supports the detection of anomalies in the state-of-health of a storage battery in a timely fashion. The proposed algorithm is subsequently applied to the storage battery of the aforementioned in-orbit satellite. The results show the following. The anomalies detected using the proposed algorithm are more reliable, effective and visual than those obtained using the conventional multivariate anomaly detection algorithms. Compared to the classic backpropagation NN-based algorithm, the DBN-based algorithm is notably advantageous in terms of the model training time and convergence.

show abstract

Optimize the Coverage Probability of Prediction Interval for Anomaly Detection of Sensor-Based Monitoring Series

Cited by 29 publications

References 47 publications

Forecasting Vegetation Condition with a Bayesian Auto-regressive Distributed Lags (BARDL) Model

Forecasting Vegetation Condition with a Bayesian Auto-regressive Distributed Lags (BARDL) Model

A Dynamic Hierarchical Bayesian Approach for Forecasting Vegetation Condition

Detection of Voltage Anomalies in Spacecraft Storage Batteries Based on a Deep Belief Network

Contact Info

Product

Resources

About