a SOM (total 39,945 measurement vectors on a 37 Â 27 map). In particular,
the relationships between flow, oxidation-reduction potential (ORP) and chlorine
can be seen as similarly shaped areas of colour in the same sections of the map
(e.g. upper right corner). The use of data analysis techniques like SOMs, which
have a good resilience to sparse data, can provide value where other techniques
would likely fail.
Other approaches to data-driven visualisation/mapping and cluster analysis
include using k-means (typically with Euclidean distance), hierarchical clustering,
distribution models (such as the expectation-maximisation algorithm), fuzzy
clustering and density-based models, e.g. DBSCAN [17], Sammon’s projection
[18] and t-SNE [19].
1.3 Hydroinformatics
Hydroinformatics has emerged over the last decade to become a recognised
and established field of independent research within the hydrological sciences.
Hydroinformatics is concerned with the development and hydrological application
of mathematical modelling, information technology, data science (e.g. data mining
and knowledge discovery, big data and deep learning techniques) and computational
intelligence tools. It provides the computer-based decision support systems that
are now becoming increasingly prevalent for use by consulting engineers, water
service providers and government agencies to implement solutions such as smart
networks.
Temperature
U-matrix
Flow
pH
0.463
0.235
0.00782
16.3
15.8
15.3
d
d
d
0.256
0.176
0.0952
7.57
7.07
6.58
Conductivity
ORP
Turbidity
Chlorine
729
571
414
429
302
175
d
d
DO
Total Chlorine
58.3
51
43.6
212
107
2.67
d
d
d
d
3.08
1.7
0.317
20.7
13.2
5.58
Fig. 3 Example SOM for water quality monitoring
8
S. R. Mounce
the relationships between flow, oxidation-reduction potential (ORP) and chlorine
can be seen as similarly shaped areas of colour in the same sections of the map
(e.g. upper right corner). The use of data analysis techniques like SOMs, which
have a good resilience to sparse data, can provide value where other techniques
would likely fail.
Other approaches to data-driven visualisation/mapping and cluster analysis
include using k-means (typically with Euclidean distance), hierarchical clustering,
distribution models (such as the expectation-maximisation algorithm), fuzzy
clustering and density-based models, e.g. DBSCAN [17], Sammon’s projection
[18] and t-SNE [19].
1.3 Hydroinformatics
Hydroinformatics has emerged over the last decade to become a recognised
and established field of independent research within the hydrological sciences.
Hydroinformatics is concerned with the development and hydrological application
of mathematical modelling, information technology, data science (e.g. data mining
and knowledge discovery, big data and deep learning techniques) and computational
intelligence tools. It provides the computer-based decision support systems that
are now becoming increasingly prevalent for use by consulting engineers, water
service providers and government agencies to implement solutions such as smart
networks.
Temperature
U-matrix
Flow
pH
0.463
0.235
0.00782
16.3
15.8
15.3
d
d
d
0.256
0.176
0.0952
7.57
7.07
6.58
Conductivity
ORP
Turbidity
Chlorine
729
571
414
429
302
175
d
d
DO
Total Chlorine
58.3
51
43.6
212
107
2.67
d
d
d
d
3.08
1.7
0.317
20.7
13.2
5.58
Fig. 3 Example SOM for water quality monitoring
8
S. R. Mounce