CN109887240A - A kind of landslide disaster safety monitoring and method for early warning based on artificial intelligence - Google Patents
A kind of landslide disaster safety monitoring and method for early warning based on artificial intelligence Download PDFInfo
- Publication number
- CN109887240A CN109887240A CN201910220808.3A CN201910220808A CN109887240A CN 109887240 A CN109887240 A CN 109887240A CN 201910220808 A CN201910220808 A CN 201910220808A CN 109887240 A CN109887240 A CN 109887240A
- Authority
- CN
- China
- Prior art keywords
- principal component
- warning
- monitoring
- landslide disaster
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Pit Excavations, Shoring, Fill Or Stabilisation Of Slopes (AREA)
- Emergency Alarm Devices (AREA)
- Alarm Systems (AREA)
Abstract
The landslide disaster safety monitoring and method for early warning that the present invention relates to a kind of based on artificial intelligence.Firstly, burying sensor element in easy landslide areas selection characteristic point, sequential parameter of all types of rock-soil mechanics about the time is obtained, and carry out principal component analysis, obtain principal component number and principal component characteristic valueF;Secondly, principal component characteristic value F is carried out clustering, the crucial class of landslide disaster generation, and the relationship of comparative analysis principal component characteristic value and same day principal component characteristic value are obtained, search obtains landslide disaster threshold value of warning indicatrix;Finally, obtaining predicted value with the relationship of principal component characteristic value and same day principal component characteristic value, and compared with landslide disaster threshold value of warning indicatrix, different landslide disaster safety monitoring early warning response ranks are obtained.It is low that the present invention is able to solve each module fusion degree existing for existing monitoring and warning system, multi-index monitoring data can not Unified Characterization, multi objective safe early warning threshold value cannot effectively obtain and carry out the technical problem of safe early warning.
Description
Technical field
The present invention relates to Landslide Hazards safety monitorings and early warning field, and in particular to a kind of cunning based on artificial intelligence
Slope disaster safety monitoring and method for early warning.
Background technique
China is vast in territory, is the country that a Landslide Hazards take place frequently, and counts according to China's landslide disaster statistical yearbook,
Since 1949,2 Wan Yuqi of Landslide Hazards, more than 1,000 people of injures and deaths, population suffered from disaster more than 90 occur every year on average for China
Hundred million yuan of ten thousand, direct economic loss 20-60.It " promotes sci-tech support ability and strengthens 3 years action schemes of Geological Hazards Monitoring early warning
(2018 ~ 2020) " and " national hazards control " 13 " planning " proposition, Yao Jiaqiang Prevention And Treatment of Geological Hazards, sufficiently
Using technological means, carry out comprehensive, multi-level specialized monitoring and warning, promotes China's Geological Hazards Monitoring early warning entirety skill
Art is horizontal, reduces because geological disaster causes casualties quantity.
It consults domestic and international related literatures and shows that the monitoring and warning of geological disaster is mainly unfolded from two angles, one
Class be geological disaster real-time monitoring in situ, monitoring parameters include displacement, humidity, soil pressure, ess-strain etc.;Another kind of is to adopt
It is monitored with space to ground, that is, uses synthetic aperture radar interferometry technology (InSAR), airborne laser radar technology (LiDAR),
High-definition remote sensing technology, the methods of global navigational satellite technology (GNSS) carry out geo-hazard early-warning.Landslide disaster is supervised safely
Surveying early warning, presently, there are following problems:
(1) monitoring data processing technique is weak
Landslide disaster is administered with during real-time monitoring, and China has accumulated a large amount of monitoring data at present, these data are a bit
Useful, some are redundancies, how based on using artificial intelligence approach, using with big data digging technology, are found out to landslide
The beneficial data deficiency of disaster safe early warning reliably and effective calculation method.
(2) security monitoring and early warning systems merge
Effective Landslide Hazards security monitoring and early warning systems, it is desirable that modules are mutually matched in system, form one
Organic whole correctly plays forewarning function.China focuses on using various advanced in landslide disaster prevention field at present
New and high technology method obtains various monitoring data, and how to support warning module for monitoring data, makes reasonable decision and lacks
Weary unification is considered and efficient system integration method.
(3) safe early warning threshold value.
Reasonable safe early warning threshold value, is the basis for obtaining correct slope disaster safe early warning.Landslide disaster is pacified at present
Engineering experience is partial in the acquisition and application of full threshold value, and has biggish randomness, and the setting property of safe early warning threshold value is horizontal to be obtained
Less than guarantee.On the other hand, for a large amount of monitoring index, at present frequently with one or two individual index as early warning
Threshold value, this is clearly inadequate.
Summary of the invention
The landslide disaster safety monitoring and method for early warning that the purpose of the present invention is to provide a kind of based on artificial intelligence, the party
Method is based on artificial intelligence approach, establishes the landslide disaster pre-warning system for monitoring that reliable, each module blends, and solves existing
Each module fusion degree of system existing for monitoring and warning system is low, multi-index monitoring data can not Unified Characterization, multi objective safety
Threshold value of warning cannot effectively obtain and carry out the technical problem of safe early warning.
To achieve the above object, the technical scheme is that a kind of landslide disaster safety monitoring based on artificial intelligence
With method for early warning, include the following steps:
(1) the landslide disaster security monitoring and early warning systems based on artificial intelligence are constructed, which includes monitoring modular, prediction mould
Block and warning module;
(2) in easy landslide areas, selection characteristic point buries sensor element;
(3) sensor element is uniformly accessed into data transmission device, data is transmitted to monitoring modular by data transmission device, are obtained
Obtain sequential parameter of all types of rock-soil mechanics about the time;
(4) redundancy analysis, preliminary data processing, rejecting abnormalities are carried out about the sequential parameter of time to all types of rock-soil mechanics;
(5) all types of rock-soil mechanics that will acquire carry out principal component analysis about the sequential parameter of time: calculating all types of rocks first
Soil mechanics about the time sequential parameter in the initial characteristic values at each moment, contribution rate and component matrix, to accumulate contribution rate
85% for critical determining time series parameters principal component number (F 1 , F 2 , F 3 , F 4 ...), it is special to obtain cumulative time-series principal component
Value indicativeF;
(6) by cumulative time-series principal component characteristic valueFIt carries out clustering: according to predicted time spacing accuracy, that is, working as prediction
When precision is day, the same day, the cumulative time-series principal component characteristic value before 2 days, before 3 days, before 5 days and before 7 days are calculated, is usedK-
Means clustering method carries out clustering, obtains the crucial class of landslide disaster generation;When similarly, predicted time spacing accuracy is,
Timesharing carries out same operation;
(7) crucial class, the cumulative time-series principal component characteristic value before comparative analysis 2 days, before 3 days, before 5 days and before 7 days are extracted
With the linear relationship of same day principal component characteristic value, search obtains landslide disaster threshold value of warning indicatrix;
(8) landslide disaster early warning three-level response rank, respectively red monitoring and warning, orange monitoring and warning, yellow monitoring are established
Early warning;When principal component characteristic value is more than landslide disaster threshold value of warning indicatrix, red monitoring and warning is issued;As principal component spy
When value indicative is more than the 85% of landslide disaster threshold value of warning indicatrix corresponding eigenvalue, orange monitoring and warning is issued;As principal component spy
When value indicative is more than the 70% of landslide disaster threshold value of warning indicatrix corresponding eigenvalue, yellow monitoring and warning is issued;
(9) prediction calculates principal component characteristic value one day after, and compared with landslide disaster threshold value of warning indicatrix, obtains early warning
Rank is responded, carries out disaster response and emergency disposal for policy-making body.
In an embodiment of the present invention, in step (2), the sensor element includes rainfall gauge, psychrometer, hole
Water pressure gauge, soil moisture content sensor, earth pressure gauge, displacement meter.
In an embodiment of the present invention, in step (3), sequential parameter packet of all types of rock-soil mechanics about the time
It includes: rainfall, air humidity, pore water pressure, soil moisture, slope foot soil pressure, top of the slope soil pressure, side slope soil pressure, displacement
Parameter.
Compared to the prior art, it the invention has the following advantages: the present invention is based on artificial intelligence approach, establishes reliable
, the landslide disaster pre-warning system for monitoring that each module blends, solve each mould of system existing for existing monitoring and warning system
Block fusion degree is low, multi-index monitoring data can not Unified Characterization, multi objective safe early warning threshold value cannot obtain effectively and be carried out
The technical problem of safe early warning.
Detailed description of the invention
Fig. 1 is landslide disaster security monitoring and early warning systems structural schematic diagram of the present invention.
Fig. 2 is landslide disaster safety monitoring of the present invention and threshold value of warning indicatrix schematic diagram.
Specific embodiment
With reference to the accompanying drawing, technical solution of the present invention is specifically described.
The landslide disaster safety monitoring and method for early warning that the present invention provides a kind of based on artificial intelligence, firstly, easily sliding
Slope regional choice characteristic point buries sensor element, obtains sequential parameter of all types of rock-soil mechanics about the time, and led
At analysis, principal component number and principal component characteristic value are obtainedF;Secondly, principal component characteristic value F is carried out clustering, obtain
The crucial class that landslide disaster occurs, and the relationship of comparative analysis principal component characteristic value and same day principal component characteristic value, search obtain
Landslide disaster threshold value of warning indicatrix;Finally, being obtained with the relationship of principal component characteristic value and same day principal component characteristic value pre-
Measured value, and compared with landslide disaster threshold value of warning indicatrix, obtain different landslide disaster safety monitoring early warning response ranks.
The following are specific implementation examples of the invention.
This example is directed to the town Quanzhou, Fujian city Anxi County Xi Ping Yao mountain village, and early period, side slope temporarily occurred in Heavy Rain of Typhoon
Extensive landslide, has taken preliminary slope reinforcement measure at present, is badly in need of establishing reliable Real-time security monitoring in village's side slope
With early warning system.Specific implementation step is:
(1) in easy landslide areas, selection characteristic point buries sensor element, including rainfall gauge, psychrometer, pore water pressure
Meter, soil moisture content sensor, earth pressure gauge, displacement meter.
(2) sensor is uniformly accessed into data transmission device, is passed by wireless data transfer module to the monitoring modular of system
Transmission of data is divided into point (min) between data obtaining time.Obtain 8 time series parameters: rainfall (mm), air humidity (%),
Pore water pressure (kPa), soil moisture (%), slope foot soil pressure (kPa), top of the slope soil pressure (kPa), side slope soil pressure (kPa),
It is displaced (mm).
(3) redundancy analysis, preliminary data processing, rejecting abnormalities are carried out to time series parameters.
(4) the 8 class time series parameters that will acquire carry out principal component analysis.8 class time series parameters are calculated first each
Initial characteristic values, contribution rate and the component matrix at moment, to accumulate contribution rate 85% for critical determining time series parameters principal component
Number (F 1 , F 2 , F 3 , F 4 ), obtain time series principal component characteristic valueF。
(5) cumulative time-series principal component characteristic value is subjected to clustering.Calculate the same day, before 2d, before 3d, before 5 days and 7
Cumulative time-series principal component characteristic value before it, with cluster (K- means) method progress clustering, obtain landslide disaster
The crucial class of generation.
(6) crucial class is extracted, before comparative analysis 2d, the cumulative time-series principal component feature before 3d, before 5 days and before 7 days
The linear relationship of value and same day principal component characteristic value, search obtain landslide disaster threshold value of warning indicatrix.
(7) establishing landslide disaster early warning three-level response rank, (red monitoring and warning, orange monitoring and warning, yellow monitoring are pre-
It is alert).When principal component characteristic value is more than landslide disaster threshold value of warning indicatrix, red monitoring and warning is issued;As principal component spy
When value indicative is more than the 85% of landslide disaster threshold value of warning indicatrix corresponding eigenvalue, orange monitoring and warning is issued;As principal component spy
When value indicative is more than the 70% of landslide disaster threshold value of warning indicatrix corresponding eigenvalue, yellow monitoring and warning is issued;
(8) prediction calculates principal component characteristic value one day after, and compared with landslide disaster threshold value of warning indicatrix, obtains early warning
Rank is responded, carries out disaster response and emergency disposal for policy-making body.
The above are preferred embodiments of the present invention, all any changes made according to the technical solution of the present invention, and generated function is made
When with range without departing from technical solution of the present invention, all belong to the scope of protection of the present invention.
Claims (3)
1. a kind of landslide disaster safety monitoring and method for early warning based on artificial intelligence, which comprises the steps of:
(1) the landslide disaster security monitoring and early warning systems based on artificial intelligence are constructed, which includes monitoring modular, prediction mould
Block and warning module;
(2) in easy landslide areas, selection characteristic point buries sensor element;
(3) sensor element is uniformly accessed into data transmission device, data is transmitted to monitoring modular by data transmission device, are obtained
Obtain sequential parameter of all types of rock-soil mechanics about the time;
(4) redundancy analysis, preliminary data processing, rejecting abnormalities are carried out about the sequential parameter of time to all types of rock-soil mechanics;
(5) all types of rock-soil mechanics that will acquire carry out principal component analysis about the sequential parameter of time: calculating all types of rocks first
Soil mechanics about the time sequential parameter in the initial characteristic values at each moment, contribution rate and component matrix, to accumulate contribution rate
85% for critical determining time series parameters principal component number (F 1 , F 2 , F 3 , F 4 ...), it is special to obtain cumulative time-series principal component
Value indicativeF;
(6) by cumulative time-series principal component characteristic valueFIt carries out clustering: according to predicted time spacing accuracy, that is, working as prediction
When precision is day, the same day, the cumulative time-series principal component characteristic value before 2 days, before 3 days, before 5 days and before 7 days are calculated, is usedK-
Means clustering method carries out clustering, obtains the crucial class of landslide disaster generation;When similarly, predicted time spacing accuracy is,
Timesharing carries out same operation;
(7) crucial class, the cumulative time-series principal component characteristic value before comparative analysis 2 days, before 3 days, before 5 days and before 7 days are extracted
With the linear relationship of same day principal component characteristic value, search obtains landslide disaster threshold value of warning indicatrix;
(8) landslide disaster early warning three-level response rank, respectively red monitoring and warning, orange monitoring and warning, yellow monitoring are established
Early warning;When principal component characteristic value is more than landslide disaster threshold value of warning indicatrix, red monitoring and warning is issued;As principal component spy
When value indicative is more than the 85% of landslide disaster threshold value of warning indicatrix corresponding eigenvalue, orange monitoring and warning is issued;As principal component spy
When value indicative is more than the 70% of landslide disaster threshold value of warning indicatrix corresponding eigenvalue, yellow monitoring and warning is issued;
(9) prediction calculates principal component characteristic value one day after, and compared with landslide disaster threshold value of warning indicatrix, obtains early warning
Rank is responded, carries out disaster response and emergency disposal for policy-making body.
2. a kind of landslide disaster safety monitoring and method for early warning based on artificial intelligence according to claim 1, feature
It is, in step (2), the sensor element includes rainfall gauge, psychrometer, pore pressure gauge, soil moisture content biography
Sensor, earth pressure gauge, displacement meter.
3. a kind of landslide disaster safety monitoring and method for early warning based on artificial intelligence according to claim 1, feature
It is, in step (3), all types of rock-soil mechanics include: rainfall, air humidity, hole about the sequential parameter of time
Water pressure, soil moisture, slope foot soil pressure, top of the slope soil pressure, side slope soil pressure, displacement parameter.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910220808.3A CN109887240A (en) | 2019-03-22 | 2019-03-22 | A kind of landslide disaster safety monitoring and method for early warning based on artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910220808.3A CN109887240A (en) | 2019-03-22 | 2019-03-22 | A kind of landslide disaster safety monitoring and method for early warning based on artificial intelligence |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109887240A true CN109887240A (en) | 2019-06-14 |
Family
ID=66933757
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910220808.3A Pending CN109887240A (en) | 2019-03-22 | 2019-03-22 | A kind of landslide disaster safety monitoring and method for early warning based on artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109887240A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110516875A (en) * | 2019-08-28 | 2019-11-29 | 江西理工大学 | A kind of building of slump Accident analysis model and slump accidents early warning method, system |
CN111006593A (en) * | 2019-12-13 | 2020-04-14 | 武汉纵横天地空间信息技术有限公司 | Method and system for monitoring mountain landform and predicting landslide by using unmanned aerial vehicle |
CN111623812A (en) * | 2020-06-28 | 2020-09-04 | 河海大学 | Horizontal testing device and method based on fiber bragg grating |
CN111784976A (en) * | 2020-06-30 | 2020-10-16 | 杭州鲁尔物联科技有限公司 | Mountain torrent disaster early warning method, device, system and storage medium |
CN112767656A (en) * | 2021-01-05 | 2021-05-07 | 中铁十九局集团矿业投资有限公司 | Open mine landslide disaster early warning method and system |
CN113593207A (en) * | 2021-06-18 | 2021-11-02 | 哈尔滨理工大学 | Pore water pressure online monitoring and early warning system and method based on 5G network |
CN113781745A (en) * | 2021-08-20 | 2021-12-10 | 合肥星北航测信息科技有限公司 | Beidou and micromotion landslide early warning method based on K-means clustering algorithm |
CN114863643A (en) * | 2022-04-25 | 2022-08-05 | 浙江科技学院 | Early warning method for rainfall type landslide based on GIS area |
CN115565337A (en) * | 2022-10-26 | 2023-01-03 | 山东科技大学 | Landslide disaster early warning system based on geological disaster management and control |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104299367A (en) * | 2014-10-23 | 2015-01-21 | 中国科学院、水利部成都山地灾害与环境研究所 | Landslide hazard multi-stage comprehensive monitoring and early warning method |
CN105788180A (en) * | 2016-04-14 | 2016-07-20 | 中国科学院、水利部成都山地灾害与环境研究所 | Shallow rainfall-induced landslide early-warning method based on unsaturated soil mass water content |
CN105869100A (en) * | 2016-04-29 | 2016-08-17 | 中国地质大学(武汉) | Method for fusion and prediction of multi-field monitoring data of landslides based on big data thinking |
CN106650767A (en) * | 2016-09-20 | 2017-05-10 | 河海大学 | Flood forecasting method based on cluster analysis and real time correction |
CN107516402A (en) * | 2017-10-01 | 2017-12-26 | 中国科学院、水利部成都山地灾害与环境研究所 | Regional Landslide disaster rainfall method for early warning, early warning system |
CN107610421A (en) * | 2017-09-19 | 2018-01-19 | 合肥英泽信息科技有限公司 | A kind of geo-hazard early-warning analysis system and method |
CN109003422A (en) * | 2018-08-02 | 2018-12-14 | 北京大学深圳研究生院 | Monitoring data processing method and landslide forecasting procedure for landslide |
CN109146144A (en) * | 2018-07-26 | 2019-01-04 | 西安工程大学 | Based on the landslide disaster prediction technique for improving Bayesian network |
CN109272721A (en) * | 2018-11-01 | 2019-01-25 | 西安工程大学 | Landslide disaster forecasting procedure based on KPCA-FOA-LSSVM |
-
2019
- 2019-03-22 CN CN201910220808.3A patent/CN109887240A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104299367A (en) * | 2014-10-23 | 2015-01-21 | 中国科学院、水利部成都山地灾害与环境研究所 | Landslide hazard multi-stage comprehensive monitoring and early warning method |
CN105788180A (en) * | 2016-04-14 | 2016-07-20 | 中国科学院、水利部成都山地灾害与环境研究所 | Shallow rainfall-induced landslide early-warning method based on unsaturated soil mass water content |
CN105869100A (en) * | 2016-04-29 | 2016-08-17 | 中国地质大学(武汉) | Method for fusion and prediction of multi-field monitoring data of landslides based on big data thinking |
CN106650767A (en) * | 2016-09-20 | 2017-05-10 | 河海大学 | Flood forecasting method based on cluster analysis and real time correction |
CN107610421A (en) * | 2017-09-19 | 2018-01-19 | 合肥英泽信息科技有限公司 | A kind of geo-hazard early-warning analysis system and method |
CN107516402A (en) * | 2017-10-01 | 2017-12-26 | 中国科学院、水利部成都山地灾害与环境研究所 | Regional Landslide disaster rainfall method for early warning, early warning system |
CN109146144A (en) * | 2018-07-26 | 2019-01-04 | 西安工程大学 | Based on the landslide disaster prediction technique for improving Bayesian network |
CN109003422A (en) * | 2018-08-02 | 2018-12-14 | 北京大学深圳研究生院 | Monitoring data processing method and landslide forecasting procedure for landslide |
CN109272721A (en) * | 2018-11-01 | 2019-01-25 | 西安工程大学 | Landslide disaster forecasting procedure based on KPCA-FOA-LSSVM |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110516875B (en) * | 2019-08-28 | 2020-11-27 | 江西理工大学 | Slump accident analysis model construction and slump accident early warning method and system |
CN110516875A (en) * | 2019-08-28 | 2019-11-29 | 江西理工大学 | A kind of building of slump Accident analysis model and slump accidents early warning method, system |
CN111006593A (en) * | 2019-12-13 | 2020-04-14 | 武汉纵横天地空间信息技术有限公司 | Method and system for monitoring mountain landform and predicting landslide by using unmanned aerial vehicle |
CN111623812A (en) * | 2020-06-28 | 2020-09-04 | 河海大学 | Horizontal testing device and method based on fiber bragg grating |
CN111784976B (en) * | 2020-06-30 | 2022-02-18 | 杭州鲁尔物联科技有限公司 | Mountain torrent disaster early warning method, device, system and storage medium |
CN111784976A (en) * | 2020-06-30 | 2020-10-16 | 杭州鲁尔物联科技有限公司 | Mountain torrent disaster early warning method, device, system and storage medium |
CN112767656A (en) * | 2021-01-05 | 2021-05-07 | 中铁十九局集团矿业投资有限公司 | Open mine landslide disaster early warning method and system |
CN112767656B (en) * | 2021-01-05 | 2021-11-23 | 中铁十九局集团矿业投资有限公司 | Open mine landslide disaster early warning method and system |
CN113593207A (en) * | 2021-06-18 | 2021-11-02 | 哈尔滨理工大学 | Pore water pressure online monitoring and early warning system and method based on 5G network |
CN113781745A (en) * | 2021-08-20 | 2021-12-10 | 合肥星北航测信息科技有限公司 | Beidou and micromotion landslide early warning method based on K-means clustering algorithm |
CN113781745B (en) * | 2021-08-20 | 2023-01-31 | 合肥星北航测信息科技有限公司 | Beidou and micromotion landslide early warning method based on K-means clustering algorithm |
CN114863643A (en) * | 2022-04-25 | 2022-08-05 | 浙江科技学院 | Early warning method for rainfall type landslide based on GIS area |
CN114863643B (en) * | 2022-04-25 | 2023-09-22 | 浙江科技学院 | Rainfall landslide early warning method based on GIS region |
CN115565337A (en) * | 2022-10-26 | 2023-01-03 | 山东科技大学 | Landslide disaster early warning system based on geological disaster management and control |
CN115565337B (en) * | 2022-10-26 | 2024-03-19 | 山东科技大学 | Landslide disaster early warning system based on geological disaster management and control |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109887240A (en) | A kind of landslide disaster safety monitoring and method for early warning based on artificial intelligence | |
Zhuang et al. | A coupled slope cutting—a prolonged rainfall-induced loess landslide: a 17 October 2011 case study | |
CN103743441B (en) | The polynary of a kind of side slope safety is coupling in line monitoring system and method | |
CN105804094B (en) | A kind of dangerous determination methods of rock landslip and its application | |
CN104408899B (en) | Mountain highway granite residual colluvial soil landslide remote real-time early-warning method | |
CN104281920A (en) | Tailing pond layered index safety assessment and early-warning method and system | |
CN106150485B (en) | A kind of drilling well leakage forecasting system based on digital rock mass | |
CN105513285A (en) | Glacier lake outburst pre-warning method | |
CN109118718B (en) | Construction method of rainfall I-D curve threshold of debris flow and watershed debris flow early warning method | |
CN110795812B (en) | Landslide prediction method and system based on big data analysis | |
CN102867110A (en) | Rainstorm disaster risk evaluation method for foundation slope of transmission line tower | |
CN104318103A (en) | Landslide hazard monitoring and early warning rainfall threshold judging method | |
CN114333249A (en) | Landslide early warning method and device | |
CN105847410A (en) | Sponge city GIS intelligent online safety monitoring system and monitoring method | |
CN113326756A (en) | Method for identifying potential landslide hazard of reservoir bank based on rock mass degradation characteristics | |
Spence | Hydrological processes and streamflow in a lake dominated watercourse | |
CN105761436A (en) | Red bed region landslide early warning method and application thereof | |
CN104867294B (en) | A kind of in-situ ionic rare earth leaching mine landslide on-line monitoring method for early warning | |
CN102913285B (en) | Mine roof hazard warning method | |
CN103530516B (en) | A kind of meizoseismal area rubble flow hidden danger point method for quickly identifying | |
CN103530525B (en) | A kind of improve the tailing dam method based on the risk assessment accuracy of reservoir level | |
CN116564065A (en) | Mine disaster prediction and early warning method combining on-site monitoring and numerical simulation | |
CN113742827B (en) | Highway slope monitoring network system construction method based on finite difference analysis | |
Penny et al. | A process‐based approach to attribution of historical streamflow decline in a data‐scarce and human‐dominated watershed | |
CN105701976A (en) | Water and soil maintenance monitoring system based on satellite remote sensing images |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190614 |