9th Conference on Limestone Hydrogeology in Besançon

9ième Colloque d'Hydrogéologie en Pays

Calcaire à BesançonSession 4

Metrology and data transmission

“Artificial neural network for karst aquifer sustainable

management”

Marc Lambert

Manager of Syndicat des Eaux du Vivier

2

The Syndicat des Eaux du Vivier« SEV » in a few figures

– 5 municipalities including the city of Niort

– about 100.000 people depending on the Vivier karstic spring

– 650 km water networks, 36000 compteurs, 5 main water resources

– 60 agents, in public management– Hospitals, industry with SEVESO sites,

schools…)

9th Conference on Limestone Hydrogeology in Besançon

3

What are the mains problems?– Agricultural area with intensive

production– Competition with water supply– Limited and fragile underground

resources, with 2 observed karstic collapses in Vivier spring

– Quality problems due to nitrates and pesticides

9th Conference on Limestone Hydrogeology in Besançon

4

Our main purposes about quantity

– Securize water supply on our area– Understand and anticipate needs

(peaks, periodicity)– Understand and modelize water

resources (rain effect, cycles, pumping effects…)

– Criterion:

« water resources always > peak needs »

9th Conference on Limestone Hydrogeology in Besançon

5

Geological context9th Conference on Limestone Hydrogeology in Besançon

6

Geological context (AB cut)9th Conference on Limestone Hydrogeology in Besançon

7

Vivier karst observed behaviour

9th Conference on Limestone Hydrogeology in Besançon

8

Effects of pumpings forirrigation and water supply

9th Conference on Limestone Hydrogeology in Besançon

IMPACT DES PRELEVEMENTS AGRICOLES SUR LA RESSOURCE DE NIORT

-3.00

-2.00

-1.00

0.00

1.00

2.00

3.00

oct-01 avr-02 oct-02 avr-03 oct-03 avr-04 oct-04

SEMESTRES SECS / DE RECHARGE

Dé

bit

So

urc

e (

m3

/s)

/Niv

Pu

its

(-m

)

0.00

0.10

0.20

0.30

0.40

0.50

0.60

0.70

0.80

0.90

1.00

PR

EL

EV

EM

EN

TS

(A

EP

/AG

RI)

m3

/s

canal

rabattement dans lepuits du Vivier (m)

besoin Niort (V+G)(m3/s moyensmensuels)

Irrigation (m3/smoyens mensuels)données estiméespour secteur 13

9

Methodology followed– 1 : Data collecting, selecting…and mining

(ACP, geostatistics, wavelets…)– 2 : Modelling with different techniques

(lumped modelling of rainfall – runoff and rainfall aquifer level, inverse modelling using fourier analysis, neural networks…)

– 3: Forecasting with rainfall simulation– 4: Managing resources…ie how to keep

« water resources always > peak needs »

9th Conference on Limestone Hydrogeology in Besançon

10

Rainfall data analysis9th Conference on Limestone Hydrogeology in Besançon

11

Inverse modelling (TEMPO BRGM)

9th Conference on Limestone Hydrogeology in Besançon

12

Inverse modelling (TEMPO BRGM)

9th Conference on Limestone Hydrogeology in Besançon

13

Hydrological modelling (GARDENIA BRGM)

9th Conference on Limestone Hydrogeology in Besançon

RUMAX déficit maximal du sol

RUIPER Hauteur d'équiRuissellement Percolation

THG Temps ½ percolation

Percolation(RECHARGE de la nappe)

PLUIE EFFICACE

Q = SURF * EC + Qo NP = G / S + NB

Écoulement total(DEBIT du cours d'eau)

Niveau Piézom. NPDébit Q

PLUIE ETP

Surface du bassin versant

14

Hydrological modelling (GARDENIA BRGM)

9th Conference on Limestone Hydrogeology in Besançon

15

Artificial neural network modelling (Neuro one Netral)

9th Conference on Limestone Hydrogeology in Besançon

16

9th Conference on Limestone Hydrogeology in Besançon

Artificial neural network modelling

17

9th Conference on Limestone Hydrogeology in Besançon

Example of use of this model:Crisis anticipation and management

CROISEMENT ENTRE RESSOURCES DISPONIBLES ET BESOINS - ETIAGE 2005

0

10000

20000

30000

40000

50000

60000

70000

80000

01/01/05 01/07/05 01/01/06

vo

lum

es

en

m3

/j

-3.5

-3

-2.5

-2

-1.5

-1

-0.5

0

0.5

rab

att

eme

nt

(<0

) et

plu

ie (>

0)

en

m

Ress.princ.V+GI+GIII+Canal(m3/j)

Consommationm3/j

Secoursnécessaire m3/j

pluies (m)

rabattementVivier (m)

18

9th Conference on Limestone Hydrogeology in Besançon

Conclusion: advantages of ANN tools

– After choosing a good model, easy qnalytical formulation under Excel…

– « Intelligent » black box, but to use under constraints (learning sets must include extrem years)

– Easy to use for simulations (pumpings for irrigation or water supply, climate…)

– Easy to use for sensitivity analysis