Application Management Platform of Hydrological Water Resources
Monitoring Data Based on Data Mining
Jie Zhao
1,*
and Yingjie Wang
2
1
Middle Stream Hydrology and Water Resources Bureau of Yellow River Conservancy Commission, Yulin City, Shaanxi
Province, The People's Republic of China
2
Middle Stream Hydrology and Water Resources Bureau of Yellow River Conservancy Commission, Jinzhong City, Shanxi
Province, The People's Republic of China
Keywords: Computer, Data Mining Techniques, Hydrological and Water Resources Monitoring Data Application
Management Platform, Monitor Data.
Abstract: Hydrological water resources monitoring data is one of the water conservancy information resources.
Scientific research can accelerate the informatization of hydrological and hydraulic conservancy, so as to
better monitor hydrological water resources. Ordinary methods cannot solve the problem of low accuracy of
monitoring data of hydrological water resources. Therefore, this paper proposes a data mining technique for
monitoring data analysis. First of all, the computer is used to analyze the monitoring data, and the indicators
are divided according to the requirements of the monitoring data to reduce the monitoring data in the
interfering factor. Then, the computer analyzes the monitoring data of the hydrological and water resources
monitoring data application management platform to form a monitoring data scheme and correct
Comprehensive analysis of monitoring data results. MATLAB simulation shows that under certain evaluation
criteria, the accuracy of monitoring data of the hydrological and water resources monitoring data application
management platform by data mining technology is The reliability of the monitoring data is better than that
of ordinary methods.
1 INTRODUCTION
With the increasing scarcity of water resources and
the continuous deterioration of the water
environment, the monitoring and management of
hydrological resources has become the focus of
attention. Traditional hydrological resources
monitoring and management methods are constrained
by scattered data sources (Abd Elrahman and S. I. M,
et al. 2023), low data quality and low data processing
efficiency, which are difficult to meet the needs of
modern water resources management (Ashu, and Lee,
2023). The data mining method can propose effective
solutions to the above problems, optimize and
improve the hydrological resources monitoring and
management platform, and the optimized platform
can obtain (Belleflamme, and Goergen, et al. 2023),
process and analyze the data of hydrological
resources more accurately, and provide more
scientific, reasonable and effective decision-making
support for water resources management (Cai, and
Wang, et al. 2023). In this paper, we will introduce
the optimization method and application examples of
data mining methods for hydrological resources
monitoring and management platform (Campbell,
and Hyslop, 2023).
Data mining is the process of extracting potential,
useful, unknown, and previously undiscovered
patterns and patterns from massive amounts of data
(Chaparro, and O'Farrell, et al. 2023), which
transforms large amounts of data into useful
information and knowledge through a series of data
processing and analysis steps (Chen, and Tseng, et al.
2023). The main steps of a data mining method
include the following:
Data preprocessing is a key step of data mining,
including data cleaning, missing value processing,
outlier handling, etc., to make data more
standardized, complete and accurate (Chitra-Tarak,
and Warren, 2023).
Data integration is the consolidation of data from
multiple data sources under the same platform for
easy data processing and analysis (de Bruijn, and
Smilovic, et al. 2023).
Zhao, J. and Wang, Y.
Application Management Platform of Hydrological Water Resources Monitoring Data Based on Data Mining.
DOI: 10.5220/0013538800004664
Paper published under CC license (CC BY-NC-ND 4.0)
In Proceedings of the 3rd International Conference on Futuristic Technology (INCOFT 2025) - Volume 1, pages 233-238
ISBN: 978-989-758-763-4
Proceedings Copyright © 2025 by SCITEPRESS – Science and Technology Publications, Lda.
233

Data conversion is the conversion of raw data into
a form that can be processed by computers, such as
converting data into numeric, text, and other formats
(Dunea, and Serban, et al. 2023).
Pattern discovery is the core of data mining,
which discovers patterns and regularities in data
through various algorithms and models, such as
clustering, classification, regression, association rule
mining, etc (Gaillot, and Delbart, et al. 2023).
Pattern evaluation is to evaluate the validity and
accuracy of the excavated patterns to improve the
reliability and effectiveness of decision-making (Gao,
and Xu, et al. 2023).
Through the analysis and modeling of historical
data, future changes and trends of water resources can
be predicted and simulated, such as predicting water
level, flow, water quality and other indicators, so as
to provide scientific and accurate decision-making
support for water resources management (Gao, and
Wang, et al. 2023).
The mining of monitoring data can analyze the
quality of monitoring data, such as the accuracy,
consistency and completeness of monitoring data, to
ensure the validity and reliability of monitoring data
(Greco, and Marino, et al. 2023).
Through the analysis and modeling of monitoring
data, reasonable water resources management
strategies can be determined, such as quantitative
analysis of water supply and demand balance, and
formulation of water resource utilization plans, so as
to provide scientific and effective guidance for water
resources management (Guo, and Jin, et al. 2023).
Through data cleaning, outlier value processing,
missing value processing and other methods, the
quality and accuracy of monitoring data are
improved, so as to ensure the effectiveness and
reliability of data mining.
Through clustering, classification, association
rule mining and other methods, the rules, trends and
patterns in the data are discovered, so as to provide
scientific and accurate information support for water
resources management.
Monitoring data is useful for studying
hydrological water resources. However, in the
process of monitoring data, there is a problem of poor
accuracy in the monitoring data scheme, which brings
resistance to water conservancy research. Some
scholars believe that the application of data mining
technology to the analysis of hydrological and water
resources monitoring data application management
platform can effectively analyze the monitoring data
scheme and provide corresponding support for the
monitoring data. On this basis, this paper proposes a
data mining technique to optimize the monitoring
data scheme and verify the effectiveness of the model.
2 RELATED CONCEPTS
2.1 Mathematical Description of Data
Mining Techniques
Data mining technology is to use the computer to
optimize the monitoring data scheme, and according
to the indicators in the monitoring data is
i
q
, find the
unqualified values in the hydrological and water
resources monitoring data application management
platform is
i
c
, and monitor the data the scheme is
integrated is
(
iij
tol q n⋅ ）
, and the feasibility of the
hydrological water resources monitoring data
application management platform is finally judged,
and the calculation is shown in Equation (1).

(3)max(2)
iij ij ij
tol q n q n⋅+ = ≥ ÷
(1
)
Among them, the judgment of outliers is shown in
Equation (2).
22
1
1
max( ) ( 5) ( ( ) )
3
n
ij ij ij ij
i
nn meannT n
=
=⋅ +⋅+



(2
)
Data mining technology combines the advantages
of computers and uses the application management
platform of hydrological and water resources
monitoring data for quantification, which can
improve the accuracy of monitoring data.
Hypothesis I. The monitoring data requirements is
i
n
, the monitoring data scheme is
i
set
, the
satisfaction of the monitoring data scheme is
i
q
, and
the monitoring data scheme judgment function is
(0)
i
Tn≈
as shown in Equation (3).
1
() 3 2
q
ii i
i
T
j
nT
j
ξ
=
=−⋅ ⋅→


 


(3
)
2.2 Choice of Monitoring Data Scheme
Hypothesis II. The function of the hydrological water
resources monitoring data application management
INCOFT 2025 - International Conference on Futuristic Technology
234

platform is
()
i
an
, and the weight coefficient is
i
b
,
then, the monitoring data requires the unqualified
hydrological water resources monitoring data
application management platform as shown in
Equation (4).
1
1
()= 3 ()3
2
n
iii ii
i
an b c T j b
=
⋅− ⋅ ÷ + −
∏

(4)
Based on hypotheses I and II, a comprehensive
function of the monitoring data can be obtained, and
the result is shown in Equation (5).
() () max( )
ii ij
an T j n+≤
(5
)
In order to improve the effectiveness of quality
assessment, all data needs to be standardized and the
results are shown in Equation (6).

2
1
1
() () ( ( ) )
3
n
i i ij ij
i
an T j mean n T n
=
+↔ +⋅+

(6)
2.3 Analysis of Monitoring Data
Programmes
Before carrying out data mining technology, it is
necessary to analyze the monitoring data scheme in
multiple aspects, and map the monitoring data
requirements to the hydrological and water resources
monitoring data application management platform
library, and eliminate the unqualified Monitoring data
programmes is
()
i
No n
,According to Equation (6),
the anomaly evaluation scheme can be proposed, and
the results are shown in Equation (7).

2
1
() ()
()
1
(( )
)
3
ii
i
n
ij ij
i
an T j
No x
mean n T n
=
+
=
+⋅+

(7
)
Among them,

2
1
() ()
1
1
(( ) )
3
ii
n
ij ij
i
an T j
mean n T n
=
+
≤
+⋅+

it is stated that the scheme needs to be proposed,
otherwise the scheme integration required is
()
i
Z
hn
, and the result is shown in Equation (8).

() min[ () ()]
iii
Z
hn an T j=+

(8)
The hydrological and water resources monitoring
data application management platform conducts
comprehensive analysis, and sets the threshold and
index weight of the monitoring data scheme to ensure
the accuracy of data mining technology. The
application management platform of hydrological
and water resources monitoring data is a systematic
test monitoring data scheme, which needs to be
correctly analyzed. If the hydrological and water
resources monitoring data application management
platform is in a non-normal distribution is
()
i
unno n
, its monitoring data scheme will be affected,
reducing the accuracy of the overall monitoring data
is
()
i
accur n
, and the calculation result is shown in
Equation (9). 。


min[ ( ) ( )]
( ) 100%
() ()
ii
i
ii
an T j
accur n
an T j
+
=×
+


(9
)
The survey and monitoring data scheme shows
that the monitoring data scheme presents a
multidimensional distribution, which is in line with
objective facts. The application management
platform of hydrological and water resources
monitoring data is not directional, indicating that the
monitoring
data scheme has strong randomness, so it is
regarded as a high analysis study. If the random
function of the hydrological water resources
monitoring data application management platform is
()
i
randon n
, then the calculation of Equation (9)
can be expressed as Equation (10).


min[ ( ) ( )]
( ) 100% (
)
() ()
ii
ii
ii
an T j
accur n randon n
an T j
+
=×+
+


(10
)
Among them, the hydrological water resources
monitoring data application management platform
meets the normal requirements, mainly the computer
adjusts the hydrological and water resources
monitoring data application management platform,
removes duplicate and irrelevant schemes, and
supplements the default scheme, so that the dynamic
correlation of the entire monitoring data scheme is
strong.
Application Management Platform of Hydrological Water Resources Monitoring Data Based on Data Mining
235

3 OPTIMIZATION STRATEGY
OF HYDROLOGICAL WATER
RESOURCES MONITORING
DATA APPLICATION
MANAGEMENT PLATFORM
Data mining technology adopts random optimization
strategy for the hydrological and water resources
monitoring data application management platform,
and adjusts the monitoring data parameters to realize
the scheme optimization of the hydrological water
resources monitoring data application management
platform. Data mining technology divides the
hydrological and water resources monitoring data
application management platform into different
monitoring data levels, and randomly selects different
schemes. In the iterative process, the monitoring data
schemes of different monitoring data levels are
optimized and analyzed. After the optimization
analysis is completed, the monitoring data level of
different schemes is compared, and the best
hydrological and water resources monitoring data
application management platform is recorded.
4 PRACTICAL CASE OF
HYDROLOGICAL WATER
RESOURCES MONITORING
DATA APPLICATION
MANAGEMENT PLATFORM
4.1 Presentation of Monitoring Data
In order to facilitate the monitoring data, the
application management platform of hydrological
water resources monitoring data in complex
situations is taken as the research object, with 12
paths and a test time of 12h, and the specific
hydrological water resources monitoring data
application management platform is taken The
monitoring data scheme is shown in Table 1.
Table 1: Monitoring data requirements
Scope of
a
pp
lication
grade Accuracy Monitor
data
water level normal 85.34 84.82
Highe
r
82.58 88.74
flow rate normal 82.97 83.39
Hi
g
he
r
84.63 85.94
evaporate normal 85.16 86.20
Hi
g
he
r
85.16 80.34
The process of monitoring data in Table 1. is
shown in Figure 1.
Compared with ordinary methods, the monitoring
data scheme of data mining technology is closer to the
actual monitoring data requirements. In terms of the
rationality and accuracy of the hydrological and water
resources monitoring data application management
platform, data mining technology is superior to
ordinary methods. Through the change of monitoring
data scheme in Figure 2, it can be seen that the
stability of data mining technology is better and the
judgment speed is faster. Therefore, the data mining
technology has better monitoring data scheme speed,
monitoring data scheme positive accuracy, and
summation stability.
Data reliability
Water conservancy
information
resources
Monitoring
data
Data mining
technology
Data
accuracy
Hydrology
and water
resources
Figure 1: Analysis process of hydrological water resources
monitoring data application management platform
4.2 Application and Management
Platform of Hydrological and
Water Resources Monitoring Data
The monitoring data scheme of the hydrological and
water resources monitoring data application
management platform includes non-structural
information, semi-structural information and
structural information. After the pre-selection of data
mining technology, the monitoring data scheme of the
preliminary hydrological water resources monitoring
data application management platform was obtained,
and the application management platform of
hydrological water resources monitoring data was
obtained The feasibility of the monitoring data
program is analyzed. In order to more accurately
verify the accuracy of the hydrological water
resources monitoring data application management
platform, the hydrological water resources
monitoring data application management platform
and monitoring data scheme with different
INCOFT 2025 - International Conference on Futuristic Technology
236

monitoring data levels were selected. This is shown
in Table 2.
Table 2: Monitor the overall situation of the data
programme
Cate
g
or
y
Accurac
y
Anal
y
sis Rate
Water Level 90.16 87.70
Flow Rate 85.28 88.51
Eva
p
orate 87.93 89.87
Mean 90.20 88.88
X
6
90.32 90.89
P=1.936
4.3 Monitoring Data and Stability of
Monitoring Data
To verify the accuracy of the data mining technique,
the monitoring data scheme is compared with the
common method, and the monitoring data scheme is
shown in Figure 2.
Figure 2: Monitoring data of different algorithms
It can be seen from Figure 2 that the monitoring
data of data mining technology is higher than that of
ordinary methods, but the error rate is lower,
indicating that the monitoring data of data mining
technology is relatively stable, while that of ordinary
methods Monitoring data is uneven. The average
monitoring data scheme of the above three algorithms
is shown in Table 3.
Table 3: Comparison of the accuracy of monitoring data by
different methods
algorithm Monitor
data
Magnitude
of change
error
Data mining
techniques
93.34 92.47 92.92
Normal method 92.96 90.82 91.29
P 90.26 90.57 91.18
It can be seen from Table 3 that the general
method has shortcomings in the accuracy of
monitoring data in terms of hydrological water
resources monitoring data application management
platform, and the hydrological water resources
monitoring data application management platform
has undergone significant changes. High error rate.
The monitoring data for the general results of data
mining techniques is higher and better than common
methods. At the same time, the monitoring data of
data mining technology is greater than 92%, and the
accuracy has not changed significantly. To further
verify the superiority of data mining techniques. In
order to further verify the effectiveness of the
proposed method, the data mining techniques are
generally analyzed by different methods, as shown in
Figure 3.
Figure 3: Monitoring data of data mining technology
monitoring data
It can be seen from Figure 3 that the monitoring
data of data mining technology is significantly better
than that of ordinary methods, and the reason is that
the data mining technology increases the adjustment
coefficient of the hydrological and water resources
monitoring data application management platform
and sets it Thresholds for monitoring data and
rejection of non-compliant monitoring data schemes.
5 CONCLUSIONS
Aiming at the problem that the monitoring data of the
hydrological water resources monitoring data
application management platform is not satisfactory,
this paper proposes a data mining technology, and
combines the computer to optimize the hydrological
water resources monitoring data application
management platform. At the same time, the accuracy
of monitoring data is analyzed in depth, and a
monitoring data collection is constructed. The
Application Management Platform of Hydrological Water Resources Monitoring Data Based on Data Mining
237

research shows that the data mining technology can
improve the accuracy of the hydrological water
resources monitoring data application management
platform, and can generally carry out the hydrological
water resources monitoring data application
management platform Monitor data. However, in the
process of data mining technology, too much
attention is paid to the analysis of monitoring data,
resulting in unreasonable selection of monitoring data
indicators.
REFERENCES
Abd Elrahman, S. I. M., & Ataalmanan, I. M. I.(2023)
DETERMINATION OF THE HYDROLOGICAL
AND MORPHOMETRIC CHARACTERISTICS
USING GIS. Civil and Environmental Engineering,
19(1): 39-47.
Ashu, A. B., & Lee, S.-I.(2023) Multi-Site Calibration of
Hydrological Model and Spatio-Temporal Assessment
of Water Balance in a Monsoon Watershed. Water,
15(2).
Belleflamme, A., Goergen, K., Wagner, N., Kollet, S.,
Bathiany, S., El Zohbi, J., Rechid, D., Vanderborght, J.,
& Vereecken, H.(2023) Hydrological forecasting at
impact scale: the integrated ParFlow hydrological
model at 0.6 km for climate resilient water resource
management over Germany. Frontiers in Water, 5.
Cai, J., Wang, X., Cai, Y., Wei, C., Liao, Z., Liu, D., Li, C.,
& Liu, Q.(2023) An integrated connectivity diagnostics
and dependency analysis framework for supporting
water replenishment management. Journal of
Hydrology, 620.
Campbell, G. R., & Hyslop, E. J.(2023) Technical Reports:
Methods-The Application of Temperature and Light
Intensity as Intermittency Sensors in a Temporary
Pond. Water Resources Research, 59(2).
Chaparro, G., O'Farrell, I., & Hein, T.(2023) Hydrological
conditions determine shifts of plankton
metacommunity structure in riverine floodplains
without affecting patterns of species richness along
connectivity gradients. Aquatic Sciences, 85(2).
Chen, Y.-H. R., Tseng, H.-W., Hsu, K.-C., Chen, S.-Y., Ke,
C.-C., & Chiang, L.-C.(2023) Evaluation of
hydrological responses to climate change for a data-
scarce mountainous watershed in Taiwan. Journal of
Water and Climate Change, 14(5): 1447-1465.
Chitra-Tarak, R., & Warren, J. M.(2023) Amazon drought
resilience - emerging results point to new empirical
needs. New Phytologist, 237(3): 703-706.
de Bruijn, J. A., Smilovic, M., Burek, P., Guillaumot, L.,
Wada, Y., & Aerts, J. C. J. H.(2023) GEB v0.1: a large-
scale agent-based socio-hydrological model-
simulating10 million individual farming households in
a fully distributed hydrological model. Geoscientific
Model Development, 16(9): 2437-2454.
Dunea, D., Serban, G., & Bretcan, P.(2023)
Hydroinformatic Tools and Spatial Analyses for Water
Resources and Extreme Water Events. Water, 15(3).
Gaillot, A., Delbart, C., Salvador-Blanes, S.,
Vanhooydonck, P., Desmet, M., Grangeon, T., Noret,
A., & Cerdan, O.(2023) Analysis of seasonal variation
in the hydrological behaviour of a field combining
surface and tile drainage. Agricultural Water
Management, 285.
Gao, B., Xu, Y., Sun, Y., Wang, Q., Wang, Y., & Li,
Z.(2023a) The impacts of impervious surface expansion
and the operation of polders on flooding under rapid
urbanization processes. Theoretical and Applied
Climatology.
Gao, W., Wang, Z. B., Kleinhans, M. G., Miao, C., Cui, B.,
& Shao, D.(2023b) Floodplain Connecting Channels as
Critical Paths for Hydrological Connectivity of Deltaic
River Networks. Water Resources Research, 59(4).
Greco, R., Marino, P., & Bogaard, T. A.(2023) Recent
advancements of landslide hydrology. Wiley
Interdisciplinary Reviews-Water.
Guo, W., Jin, Y., Wang, H., Zhu, Y., & Zha, H.(2023)
Hydrological Regime Alteration and Ecological Effects
of Dongting Lake During the Past 60 Years. Journal of
Basic Science and Engineering, 31(1): 24-37.
INCOFT 2025 - International Conference on Futuristic Technology
238