scholarly journals Cost-sensitive rainfall thresholds for shallow landslides

Landslides ◽  
2021 ◽  
Author(s):  
Gianluca Sala ◽  
Camilla Lanfranconi ◽  
Paolo Frattini ◽  
Giulia Rusconi ◽  
Giovanni B. Crosta
Keyword(s):  
False Alarm ◽  
False Positive ◽  
Large Scale ◽  
Rainfall Intensity ◽  
False Negative ◽  
Rainfall Threshold ◽  
False Alarms ◽  
Cost Curve ◽  
Rainfall Thresholds ◽  
Reference Cost

AbstractThe risk management of rainfall-induced landslides requires reliable rainfall thresholds to issue early warning alerts. The practical application of these thresholds often leads to misclassifications, either false negative or false positive, which induce costs for the society. Since missed-alarm (false negative) and false-alarm (false positive) cost may be significantly different, it is necessary to find an optimal threshold that accounts for and minimises such costs, tuning the false-alarm and missed-alarm rates. In this paper, we propose a new methodology to develop cost-sensitive rainfall thresholds, and we also analyse several factors that produce uncertainty, such as the accuracy of rainfall intensity values at landslide location, the time of occurrence, the minimum rainfall amount to define the non-triggering event, and the variability of cost scenarios. Starting from a detailed mapping of landslides that occurred during five large-scale rainfall events in the Italian Central Alps, we first developed rainfall threshold curves with a ROC-based approach by using both rain gauge and bias-adjusted weather radar data. Then, based on a reference cost scenario in which we quantified several cost items for both missed alarms and false alarms, we developed cost-sensitive rainfall threshold curves by using cost-curve approach (Drummond and Holte 2000). Finally, we studied the sensitivity of cost items. The study confirms how important is the information regarding rainfall intensity at the landslide site for the development of rainfall thresholds. Although the use of bias-corrected radar strongly improves these values, a large uncertainty related to the exact time of landslide occurrence still remains, negatively affecting the analysis. Accounting for the different missed-alarm and false-alarm misclassification costs is important because different combinations of these costs make an increase or decrease of the rainfall thresholds convenient. In our reference cost scenario, the most convenient threshold is lower than ROC-based thresholds because it seeks to minimise the number of missed alarms, whereas the missed-alarm costs are almost seven times greater than false-alarm costs. However, for different cost scenarios, threshold may vary significantly, as much as half an order of magnitude.

How to account for misclassification costs in shallow-landslide rainfall thresholds?

2021 ◽  
Author(s):  
Paolo Frattini ◽  
Gianluca Sala ◽  
Camilla Lanfranconi ◽  
Giulia Rusconi ◽  
Giovanni Crosta
Keyword(s):  
False Alarm ◽  
Rainfall Intensity ◽  
Rainfall Threshold ◽  
Shallow Landslides ◽  
False Alarms ◽  
Rainfall Thresholds ◽  
Rainfall Events ◽  
Misclassification Costs ◽  
Triggering Events ◽  
The Cost

<p>Rainfall is one of the most significant triggering factors for shallow landslides. The early warning for such phenomena requires the definition of a threshold based on a critical rainfall condition that may lead to diffuse landsliding. The developing of these thresholds is frequently done through empirical or statistical approaches that aim at identifying thresholds between rainfall events that triggered or non-triggered landslides. Such approaches present several problems related to the identification of the exact amount of rainfall that triggered landslides, the local geo-environmental conditions at the landslide site, and the minimum rainfall amount used to define the non-triggering events. Furthermore, these thresholds lead to misclassifications (false negative or false positive) that always induce costs for the society. The aim of this research is to address these limitations, accounting for classification costs in order to select the optimal thresholds for landslide risk management.</p><p>Starting from a database of shallow landslides occurred during five regional-scale rainfall events in the Italian Central Alps, we extracted the triggering rainfall intensities by adjusting rain gouge data with weather radar data. This adjustment significantly improved the information regarding the rainfall intensity at the landslide site and, although an uncertainty related to the exact timing of occurrence has still remained. Therefore, we identified the rainfall thresholds through the Receiver Operating Characteristic (ROC) approach, by identifying the optimal rainfall intensity that separates triggering and non-triggering events. To evaluate the effect related to the application of different minimum rainfall for non-triggering events, we have adopted three different values obtaining similar results, thus demonstrating that the ROC approach is not sensitive to the choice of the minimum rainfall threshold. In order to include the effect of misclassification costs we have developed cost-sensitive rainfall threshold curves by using cost-curve approach (Drummond and Holte 2000). As far as we know, this is the first attempt to build a cost-sensitive rainfall threshold for landslides that allows to explicitly account for misclassification costs. For the development of the cost-sensitive threshold curve, we had to define a reference cost scenario in which we have quantified several cost items for both missed alarms and false alarms. By using this scenario, the cost-sensitive rainfall threshold results to be lower than the ROC threshold to minimize the missed alarms, the costs of which are seven times greater than the false alarm costs. Since the misclassification costs could vary according to different socio-economic contexts and emergency organization, we developed different extreme scenarios to evaluate the sensitivity of misclassification costs on the rainfall thresholds. In the scenario with maximum false-alarm cost and minimum missed-alarm cost, the rainfall threshold increases in order to minimize the false alarms. Conversely, the rainfall thresholds decreases in the scenario with minimum false-alarm cost and maximum missed-alarm costs. We found that the range of variation between the curves of these extreme scenarios is as much as half an order of magnitude.</p>

scholarly journals Assessment of Rainfall Thresholds for Rain-Induced Landslide Activity in North Sikkim Road Corridor in Sikkim Himalaya, India

2019 ◽  
pp. 1-14 ◽  
Author(s):  
Bappaditya Koley ◽  
Anindita Nath ◽  
Subhajit Saraswati ◽  
Kaushik Bandyopadhyay ◽  
Bidhan Chandra Ray
Keyword(s):  
Rainfall Intensity ◽  
Lower Boundary ◽  
Daily Rainfall ◽  
Rainfall Threshold ◽  
Rainfall Data ◽  
Antecedent Rainfall ◽  
Rainfall Thresholds ◽  
Sikkim Himalaya ◽  
North East ◽  
The North

Land sliding is a perennial problem in the Eastern Himalayas. Out of 0.42 million km2 of Indian landmass prone to landslide, 42% fall in the North East Himalaya, specially Darjeeling and Sikkim Himalaya. Most of these landslides are triggered by excessive monsoon rainfall between June and October in almost every year. Various attempts in the global scenario have been made to establish rainfall thresholds in terms of intensity – duration of antecedent rainfall models on global, regional and local scale for triggering of the landslide. This paper describes local aspect of rainfall threshold for landslides based on daily rainfall data in and around north Sikkim road corridor region. Among 210 Landslides occurring from 2010 to 2016 were studied to analyze rainfall thresholds. Out of the 210 landslides, however, only 155 Landslides associated with rainfall data which were analyzed to yield a threshold relationship between rainfall intensity-duration and landslide initiation. The threshold relationship determined fits to lower boundary of the Landslide triggering rainfall events is I = 4.045 D - 0.25 (I=rainfall intensity (mm/h) and D=duration in (h)), revealed that for rainfall event of short time (24 h) duration with a rainfall intensity of 1.82 mm/h, the risk of landslides on this road corridor of the terrain is expected to be high. It is also observed that an intensity of 58 mm and 139 mm for 10-day and 20-day antecedent rainfall are required for the initiation of landslides in the study area. This threshold would help in improvement on traffic guidance and provide safety to the travelling tourists in this road corridor during the monsoon.

scholarly journals Real-bogus classification for the Zwicky Transient Facility using deep learning

2019 ◽  
Vol 489 (3) ◽  
pp. 3582-3590 ◽  
Author(s):  
Dmitry A Duev ◽  
Ashish Mahabal ◽  
Frank J Masci ◽  
Matthew J Graham ◽  
Ben Rusholme ◽  
...  
Keyword(s):  
Deep Learning ◽  
False Positive ◽  
Large Scale ◽  
Moving Objects ◽  
False Negative ◽  
Efficient Manner ◽  
Astronomical Surveys ◽  
Comparable Performance ◽  
Cost Efficient ◽  
Initial Results

ABSTRACT Efficient automated detection of flux-transient, re-occurring flux-variable, and moving objects is increasingly important for large-scale astronomical surveys. We present braai, a convolutional-neural-network, deep-learning real/bogus classifier designed to separate genuine astrophysical events and objects from false positive, or bogus, detections in the data of the Zwicky Transient Facility (ZTF), a new robotic time-domain survey currently in operation at the Palomar Observatory in California, USA. Braai demonstrates a state-of-the-art performance as quantified by its low false negative and false positive rates. We describe the open-source software tools used internally at Caltech to archive and access ZTF’s alerts and light curves (kowalski ), and to label the data (zwickyverse). We also report the initial results of the classifier deployment on the Edge Tensor Processing Units that show comparable performance in terms of accuracy, but in a much more (cost-) efficient manner, which has significant implications for current and future surveys.

scholarly journals FAFNet: A False Alarm Filter Algorithm for License Plate Detection Based on Deep Neural Network

2021 ◽  
Vol 38 (5) ◽  
pp. 1495-1501
Author(s):  
Hui Huang ◽  
Zhe Li
Keyword(s):  
Neural Network ◽  
False Alarm ◽  
Real Time ◽  
Large Scale ◽  
Real Life ◽  
Detection Algorithm ◽  
False Alarms ◽  
License Plate ◽  
Embedded Devices ◽  
License Plate Detection

The license plate detection technology has been widely applied in our daily life, but it encounters many challenges when performing license plate detection tasks in special scenarios. In this paper, a license plate detection algorithm is proposed for the problem of license plate detection, and an efficient false alarm filter algorithm, namely the FAFNet (False-Alarm Filter Network) is proposed for solving the problem of false alarms in license plate location scenarios in China. At first, this paper adopted the YOLOv5 target detection algorithm to detect license plates, and used the FAFNet to re-identify the images to avoid false detection. FAFNet is a lightweight convolutional neural network (CNN) that can solve the false alarm problem of real-time license plate recognition on embedded devices, and its performance is good. Next, this paper proposed a model generalization method for the purpose of making the proposed FAFNet be applicable to the license plate false alarm scenarios in other countries without the need to re-train the model. Then, this paper built a large-scale false alarm filter dataset, all samples in the dataset came from the industries and contained a variety of complex real-life scenarios. At last, experiments were conducted and the results showed that, the proposed FAFNet can achieve high-accuracy false alarm filtering and can run in real-time on embedded devices.

scholarly journals Quantitative Analysis of the Effects of an Earthquake on Rainfall Thresholds for Triggering Debris-Flow Events

2021 ◽  
Vol 9 ◽  
Author(s):  
Shuang Liu ◽  
Kaiheng Hu ◽  
Qun Zhang ◽  
Shaojie Zhang ◽  
Xudong Hu ◽  
...  
Keyword(s):  
Debris Flow ◽  
Debris Flows ◽  
Rainfall Intensity ◽  
Focal Depth ◽  
Rainfall Threshold ◽  
Effective Rainfall ◽  
Rainfall Thresholds ◽  
Jiuzhaigou Earthquake ◽  
The Wenchuan Earthquake ◽  
The Moment

The impacts of destructive earthquakes on rainfall thresholds for triggering the debris flows have not yet been well investigated, due to lacks of data. In this study, we have collected the debris-flow records from the Wenchuan, Lushan, and Jiuzhaigou earthquake-affected areas in Sichuan Province, China. By using a meteorological dataset with 3 h and 0.1° resolutions, the dimensionless effective rainfall and rainfall intensity-duration relationships were calculated as the possible thresholds for triggering the debris flows. The pre- and post-seismic thresholds were compared to evaluate the impacts of the various intensities of earthquakes. Our results indicate that the post-quake thresholds are much smaller than the pre-seismic ones. The dimensionless effective rainfall shows the impacts of the Wenchuan, Lushan, and Jiuzhaigou earthquakes to be ca. 26, 27, and 16%, respectively. The Wenchuan earthquake has the most significant effect on lowering the rainfall intensity-duration curve. Rainfall threshold changes related to the moment magnitude and focal depth are discussed as well. Generally, this work may lead to an improved post-quake debris-flow warning strategy especially in sparsely instrumented regions.

Rainfall thresholds of the debris flows based on various rainfall intensity types in Beijing

2021 ◽  
Author(s):  
Haizhi Wang ◽  
Qingli Zeng ◽  
Bing Xu ◽  
Luqing Zhang
Keyword(s):  
Debris Flows ◽  
Rainfall Intensity ◽  
High Water ◽  
Rainfall Threshold ◽  
Limited Information ◽  
Rainfall Thresholds ◽  
Occurrence Time ◽  
Water Flows ◽  
Average Rainfall ◽  
Concert Works

Abstract Empirical rainfall thresholds derived from various types of rainfall intensities have widely used in characterizing rainfall conditions that cause debris flows and landslides. However, few works have studied the differences among these various thresholds, due to limited information on the instantaneous intensity triggering debris flows. The detail records of the storms on 21 July, 2012, 20 July, 2016, and 16 July, 2018, together with the occurrence time of debris flows, provide an opportunity to evaluate the thresholds based on various rainfall intensities. Based these data, a new rainfall threshold of debris flows is derived from the instantaneous rainfall intensity in Beijing. At the same time, the thresholds based on average rainfall intensities as used in most previous studies, including the average over the periods from the beginnings of rainfall to the occurrences of the debris flows and over the whole period of the rainstorms, are reconstructed. The result shows that the instantaneous rainfall threshold has a higher ability in separating the rainstorms inducing from those without reducing debris flows than those derived from average intensities, indicating a high accurate of the instantaneous threshold. Our data also indicate that the debris flows in Beijing should be triggered by the concert works of rainfall intensity and cumulative precipitation. Only when enough water to infiltrate, saturate, mobilize the debris sediments, and sufficient high water flows and surges caused by intensive storms to incorporate and retain the mobilized sediments, are satisfied simultaneously do the debris flows occur.

scholarly journals The false classification of extinction risk in noisy environments

2014 ◽  
Vol 281 (1787) ◽  
pp. 20132935 ◽  
Author(s):  
B. M. Connors ◽  
A. B. Cooper ◽  
R. M. Peterman ◽  
N. K. Dulvy
Keyword(s):  
False Positive ◽  
Extinction Risk ◽  
False Negative ◽  
False Alarms ◽  
Observation Error ◽  
Noisy Environments ◽  
Stochastic Variation ◽  
Process Noise ◽  
Autocorrelated Process

Abundance trends are the basis for many classifications of threat and recovery status, but they can be a challenge to interpret because of observation error, stochastic variation in abundance (process noise) and temporal autocorrelation in that process noise. To measure the frequency of incorrectly detecting a decline (false-positive or false alarm) and failing to detect a true decline (false-negative), we simulated stable and declining abundance time series across several magnitudes of observation error and autocorrelated process noise. We then empirically estimated the magnitude of observation error and autocorrelated process noise across a broad range of taxa and mapped these estimates onto the simulated parameter space. Based on the taxa we examined, at low classification thresholds (30% decline in abundance) and short observation windows (10 years), false alarms would be expected to occur, on average, about 40% of the time assuming density-independent dynamics, whereas false-negatives would be expected to occur about 60% of the time. However, false alarms and failures to detect true declines were reduced at higher classification thresholds (50% or 80% declines), longer observation windows (20, 40, 60 years), and assuming density-dependent dynamics. The lowest false-positive and false-negative rates are likely to occur for large-bodied, long-lived animal species.

scholarly journals Asymmetric Effects of False Positive and False Negative Indications on the Verification of Alerts in Different Risk Conditions

2016 ◽  
Vol 60 (1) ◽  
pp. 289-292 ◽  
Author(s):  
Rebecca Wiczorek ◽  
Joachim Meyer
Keyword(s):  
False Alarm ◽  
Information Search ◽  
False Positive ◽  
Perceived Risk ◽  
False Negative ◽  
Asymmetry Effect ◽  
Asymmetric Effects ◽  
Additional Information ◽  
Alarm Systems ◽  
Risk Condition

Indications from alerts or alarm systems can be the trigger for decisions, or they can elicit further information search. We report an experiment on the tendency to collect additional information after receiving system indications. We varied the proclivity of the alarm system towards false positive or false negative indications and the perceived risk of the situation. Results showed that false alarm-prone systems led to more frequent re-checking following both alarms and non-alarms in the high risk condition, whereas miss-prone systems led to high re-checking rates only for non-alarms, representing an asymmetry effect. Increasing the risk led to more re-checks with all alarm systems, but it had a stronger impact in the false alarm-prone condition. Results regarding the relation of risk and the asymmetry effect of false negative and false positive indications are discussed.

scholarly journals An improved rainfall-threshold approach for robust prediction and warning of flood and flash flood hazards

2020 ◽  
Author(s):  
Geraldo Moura Ramos Filho ◽  
Victor Hugo Rabelo Coelho ◽  
Emerson da Silva Freitas ◽  
Yunqing Xuan ◽  
Cristiano das Neves Almeida
Keyword(s):  
Rainfall Intensity ◽  
Flash Flood ◽  
Flash Floods ◽  
Rainfall Threshold ◽  
Probability Of Detection ◽  
False Alarms ◽  
Flood Hazards ◽  
Number Of False Alarms ◽  
Antecedent Precipitation ◽  
Hydrological Hazards

Abstract This paper presents an improved method of using threshold of peak rainfall intensity for robust flood/flash flood evaluation and warnings in the state of São Paulo, Brazil. The improvements involve the use of two tolerance levels and the delineating of an intermediate threshold by incorporating an exponential curve that relates rainfall intensity and Antecedent Precipitation Index (API). The application of the tolerance levels presents an average increase of 14% in the Probability of Detection (POD) of flood and flash flood occurrences above the upper threshold. Moreover, a considerable exclusion (63%) of non-occurrences of floods and flash floods in between the two thresholds significantly reduce the number of false alarms. The intermediate threshold using the exponential curves also exhibits improvements for almost all time steps of both hydrological hazards, with the best results found for floods correlating 8-h peak intensity and 8 days API, with POD and Positive Predictive Value (PPV) values equal to 81% and 82%, respectively. This study provides strong indications that the new proposed rainfall threshold-based approach can help reduce the uncertainties in predicting the occurrences of floods and flash floods.

scholarly journals Rainfall thresholds and flood warning: an operative case study

2009 ◽  
Vol 9 (1) ◽  
pp. 135-144 ◽  
Author(s):  
V. Montesarchio ◽  
F. Lombardo ◽  
F. Napolitano
Keyword(s):  
Precipitation Amount ◽  
Rainfall Threshold ◽  
False Alarms ◽  
Rainfall Thresholds ◽  
Flood Warning ◽  
Operative Case ◽  
Critical Discharge ◽  
Definition Of ◽  
Moisture Conditions

Abstract. An operative methodology for rainfall thresholds definition is illustrated, in order to provide at critical river section optimal flood warnings. Threshold overcoming could produce a critical situation in river sites exposed to alluvial risk and trigger the prevention and emergency system alert. The procedure for the definition of critical rainfall threshold values is based both on the quantitative precipitation observed and the hydrological response of the basin. Thresholds values specify the precipitation amount for a given duration that generates a critical discharge in a given cross section and are estimated by hydrological modelling for several scenarios (e.g.: modifying the soil moisture conditions). Some preliminary results, in terms of reliability analysis (presence of false alarms and missed alarms, evaluated using indicators like hit rate and false alarm rate) for the case study of Mignone River are presented.

Sign in / Sign up

Export Citation Format

Share Document