Opportunities for scaling up research on agricultural dynamics
•
1 like•300 views
>> PAPER http://bit.ly/FSD5_Rizzo_abstract << Use of crop sequences for data-mining of remotely sensed time series across multiple scales. Several interdisciplinary perspectives (e.g., landscape agronomy, land system science, ecoagriculture) urge agronomy to contextualize the characterization of agricultural activities within the land management system. This challenges the discipline to scale up the analysis of agricultural dynamics from farm to landscape levels, where conflicting choices may emerge about the management of natural resources. Shortcoming of data covering large areas, especially about farming practices and decision-making processes, is a major constraint. Nevertheless, we consider that segmenting the land according to the observed land cover sequences can eventually incorporate a relevant part of the farmers' medium-term decision-making processes, influenced for instance by climate changes or territorial conflicts related to local resources. Furthermore, focusing on land cover sequences may provide a consistent target of analysis across multiple scales. Our aim is to discuss the relevance of a data-mining method to handle remotely sensed data and analyze temporal and spatial agricultural dynamics in a landscape perspective. The method, originally developed to handle large and labor-demanding survey datasets, is based on the stochastic segmentation with Hidden Markov Models. It firstly identifies temporal regularities of the crop/grassland sequences, then use them to segment into homogeneous patches the study area (potentially ranging from farmland to region). Starting from a case study carried out on a 12-year time series of satellite images for the Yar watershed (Brittany, France) we address the potential contribution of this kind of approach to improve the dynamic analysis of farming systems. [...] >> More info at http://bit.ly/FSD5_Rizzo_abstract
![They
interpretationy
ofyresultsyleadsytoy
reviseqtheqmodely
parametersyinyanyiterativey
andyinteractiveyprocess
yyy
e.g., different sequence
lengths and numbers
of landscape
segments
F
S
D
Agricultural systems
by design
SEPTEMBER
7-10, 2015
MONTPELLIER
France
sampleb
points
.landbcoverbinbsampledbyears5
tV4tœ44444444444444444444444444…44444444444444444444444444444tn
.geographicb
coordinates5
5thdInternationaldSymposiumd
fordFarmingdSystemdDesign
wantqtoqknowqmore?
ridavidekfsd@gmail7com
DavideyRizzo[yPhD
fullqreferences
http(]]bit7ly]
FSD3_Rizzo_ref
Opportunities for scaling up
research on agricultural dynamics
pppp
Use–of–crop–sequences–for–databmining
of–remotely–sensed–time–series
across–multiple–scales
Davide4RizzoS4
El4Ghali4Lazrak4¹4
Jean‐François4Mari4¹4²4
Laurence4Hubert‐Moy4³4
Marc4Benoît4²
:sUMR4œè6q4HGIR74INRH‐INPT74Castanet‐Tolosan74FRH
¹ssINRA74SHD‐HSTER74Mirecourt74FRH
²ssLORIA74UMR4féVy4N4INRIH74Vandœuvre‐lès‐Nancy74FRH
³sLETG‐Rennes‐COSTEL74UMR4CNRS4péé64Université4de4Rennes4è74Rennes74FRH
DbRizzobbEGbLazrakbbJFbMaribbLbHubert-MoybbMbBenoîtp
dddddddDATA-MININGdMETHOD
temporalb
segmentation
linearbmodel
bbbbspatialb
segmentation
ergodicbmodel
.allbstatesbareb
interconnected5
model topology & hierarchy
yyylandycoveryclassificationy
qysequenceylengthy
context4wisey
approximationyofyGDy
spaceyasysimpleychain
space filling (fractal)
curve
visualisationb,binterpretation
webbdynamicbinterfaceb[-7]
agronomicd
adaptation
DATAdPREPARATION
KNOWLEDGEd
EXTRACTION
landscapeysegmentation
temporo4spatialyclasses
Scalingyupy
theyresearchyonyfarmingy
systemsyfromyplot]farmytoy
landscapeylevelywillymakeypossibleytoy
buildyfarmingysystemydesignyfromyay
landscapeqagronomyyperspectivey[C4–]
7
Thisyimpliesytoyimproveytheyunderstandingyofy
theyrelationybetweenylandypatterns[yfarmingy
practicesyandynaturalyresourcesy[H411]
7
Globaly
statisticsyindicateyay
stagnationyinytotalyyieldsy
forymajorycrops7yFurthery
improvementsyrequireyagronomistsy
toyenhanceytheywaysytheyyaddressythey
farmingyuseyofylandyandywatery[1]
7y
Consideringytheylimitednessyofythesey
resources[yimprovementsyofyfarmingy
activitiesywouldydefinitelyybenefityfromy
smarterqspatialqdesignyofycroppingyandy
mixedycrop4livestockysystemsy[G[j]
7
hypothesisq
observationyqy
modellingyofyagriculturaly
landycoverysequencesycany
incorporateyfarmers’y
medium4termy
decision4makingy
processes
Landscapessegmentationsinto4patches4of4
land4cover4sequences4is4an4innovative4
approach4to4identify4land4management4units4
relating4farmers’4choices4and4natural4
resource4management34
Perspectives:sinforming4local4planners’4
decision‐making4with4spatially4explicit4
insights4about4farming4system4dynamics34
Hence74supporting4a4shared4landscape4design4
based4on4the4diversity4in4farming4systems34
YarpcasepstudyBbabwatershedbofbq-z8b
km²b.BrittanyBbFrance5bwherebthebmainb
cropsb–bmaizeBbwheatbandbgrasslandsb–b
arebrelatedbtobindustrialbbreedingzb
Ab-9–yearbtimebseriesb.-••C–922x5bofb
satellitebimagesbwasbclassifiedbintobqblandb
coverbclassesbforbindividualbfieldb
polygonsBbthenbsampledbwithbab92mb
regularbpointbgridzb
This,approach,proved,its,applicability,at,different,scales,
ranging,from,local,farming,systems,to,large,watershed,and,
regional,areas,[16‐17]
.,
Further,implementations,are,being,developed,based,on,the,
similar,principles:,first,,identification,of,sequences,,then,
mapping,[3,18]
.
CONCLUSIONS
inputqdatay–ysampledyony
ayregularlyyspacedypointygridy
–yareyscannedywithyayfractaly
curveywhereyeachypointyholdsyay
timeysequenceyofylandycovers7y
stochasticqsegmentationy
withyhierarchicalyHiddenyMarkovy
Modelsy-HMMwywhoseyspatialystatesy
areytemporalyHMMycapableyofy
assigningyayprobabilityytoyaytimey
sequencey[1G41j]
7
keypfeaturesp
•pD15pAnalysisbofb
timebregularitiesbofb
landbcoverb
sequencesbinsteadbofb
individualblandbcoverb
changeszb
•pD25bContextbwiseb
spatialbsegmentationz
•bScalingbupbresearchbonbagriculturalbdynamicsb
requiresbhetherogeneousbandbdetailedb
databsourceszb
bbbb
•bAvailableblandbcoverbmapsbrarelybensureb
continuitybinbtimeBbseamlessbcoveringbofblargeb
areasbandbdetailedbcropbclassificationzb
bbbb
bb•bDatababoutbfarmingpmanagementbareb
difficultbtobretrievebbecauseb
ofbthebcontinuousb
adaptationsbtobcomplexb
drivingbfactorsbb[-0–-8]z
•bExistingbdatasetsbprovideb
promisingbbasesbtobreconstructb
agriculturalblandbcoverb
sequences4b
French)TerUti,)Land)Parcel)
Identification)System)(LPIS,)
differently)available)throughout)
Europe))
))))
•bAdvancesbinbremotepsensingb
canbhelpbfacingbtheblackbofbdataBb
althoughbtheblistbofbidentifiedb
cropbtypesbshouldbbebimprovedz
Reversingbthebclassicalb
spacepdominantbapproachb.focusedb
onblocalblandbcoverbchanges5btob
overcomebthebinter–annualblocalb
variabilitybofbcultivatedbcropszb
bbbbbb
Timepdominantpmodelingb
frameworkbfostersbinsteadbab
landscapebsegmentationbbasedbonb
similarblandbcoverbsequencesb
thusbmappingbspatialbunitsbofb
.potentially5bsimilarbfarmingb
practiceszb
Webdistinguishedbpermanentb
frombtemporarybgrasslandb
andbidentifiedbandblocalizedb
thebtypebofbrotationsbinbwhichb
temporarypgrasslandsb
werebinvolvedzb
bbb
•,Possible,hotspot,zones,at,the,origin,
of,the,high,nitrogen,rates,observed,for,
several,years,in,the,local,rivers.,
Althoughbinputbmapsb
derivedbfrombremoteb
sensingbwerebthematicallyblessb
diversebthanbthosebderivedbfromb
fieldbsurveysBbtime–spaceb
segmentationbrevealedbsomeb
interestingbspatialbdynamicsbofb
landbcoverbsequenceszb
Acevedof2011–
Interdisciplinary–
progress–in–food–
production…–Environ–
Conserv–,GÉSRS–JS
fMorainefetfal]f2014
Farming–system–design–for–
innovative…–Animal–GÉS.DB–SJ
Murguefetfal]f2105
Toward–integrated–water–and–
agricultural–land–management…–Land–Use–
Policy–BRÉR.–’,
Thenailfetfal]f2009
The–contribution–of–cropbrotation–organization…–Agric–
Ecosyst–Environ–S,SÉ.DJ–SM
Leenhardtfetfal]f2010
Describing–and–locating–cropping–systems…–Agron–Sustain–Dev–,DÉS,S–G
BenoîtXfRizzofetfal]f2012
Landscape–agronomyÉ–a–new–field–for–addressing–agricultural–landscape–dynamicsz–
Landsc–Ecol–SDÉS,GR–MB
Boiffinfetfal]Xf2014
Agronomieh–espaceh–territoire…–Cah–Agric–.,ÉJ.–G,
ScherrfsfMcNeelyf2008
Biodiversity–conservation–and–agricultural–sustainability…–
Philos–Trans–R–Soc–B–Biol–Sci–,’,ÉBJJ–MB
Rounsevellfetfal]f2012
Challenges–for–land–system–sciencez–Land–Use–Policy–.MÉGMM–MSD
Schallerfetfal]f2012
Combining–farmers’–decision–rules–and–landscape…–
Landsc–Ecol–.JÉB,,–B’
Rizzofetfal]f2013
Farming–systems–designing–landscapes…–
Dan–J–Geogr–SS,ÉJS–G’
MarifsfLefBerf2006f
Temporal–and–spatial–data–mining…–
Soft–Comput–SDÉBD’–SB
Marifetfal]f2013
Time–space–stochastic–modelling…–Environ–Model–Softw–
B’É.SM–.J
fLandaisfsfDeffontainesf1988
Les–pratiques–des–agriculteurs…–
Études–Rural–SDMÉS.R–RG
fDusseuxfetfal]f2011f
Identification–of–grazed–and–mown–grasslands…–’th–
Intz–Workshop–Analz–MultibTemporal–Remote–Sensz–
Imagesh–ppz–SBR–G
Mignoletfetfal]f2007
Spatial–dynamics–of–farming–practices–in–the–Seine–
basin…–Sci–Total–Environ–,JRÉS,–,.
Xiaofetfal]f2014
Modeling–the–spatial–distribution–of–crop–
sequences…–Comput–Electron–Agric–SD.ÉRS–’,
Duryfetfal]f2013
Croppingbplan–decisionbmaking–on–irrigated–
crop–farms…–Eur–J–Agron–RDÉS–SD
T7p.bScalingbupbfrombfarmbtoblandscapeb,b
multiscalebscenariobanalysisbofbagriculturalbsystems
download the poster
http(]]bit7ly]FSD5_Rizzo_poster
2 page abstract
http4AAbitzlyAFSD5_Rizzo_abstract
Morepinformation:p
LazrakbetbalzBb.submitted5b
Mappingbagriculturalblandbuseb
dynamicsbwithbremotelybsensedb
series4babgenericbdatabminingb
approachbatbabwatershedbscale
Canqmapsqofqlandq
coverqsequencesqimproveq
cross-scalequnderstandingqofq
farmingqsystems?
aim
toydiscussyay
timeydominanty
andycontextywisey
data4miningy
method
[1]
[2]
[3]
ffff
[4]
[5]
fff
[6]
[7]
fff
[8]
ffff
[9]
fff
[10]
[11]
[12]
[13]
[14]
[15]
fff
[16]
[17]
[18]
challengesdddddddddddddddddddddddddddddddddddddopportunitiesddddddddddddddddddddddddmajordnovelty](https://image.slidesharecdn.com/fsd5rizzo-150823214258-lva1-app6891/85/Opportunities-for-scaling-up-research-on-agricultural-dynamics-1-320.jpg)
Recommended
Recommended
More Related Content
More from Davide Rizzo
More from Davide Rizzo (20)
Recently uploaded
Recently uploaded (20)
Opportunities for scaling up research on agricultural dynamics
- 1. They interpretationy ofyresultsyleadsytoy reviseqtheqmodely parametersyinyanyiterativey andyinteractiveyprocess yyy e.g., different sequence lengths and numbers of landscape segments F S D Agricultural systems by design SEPTEMBER 7-10, 2015 MONTPELLIER France sampleb points .landbcoverbinbsampledbyears5 tV4tœ44444444444444444444444444…44444444444444444444444444444tn .geographicb coordinates5 5thdInternationaldSymposiumd fordFarmingdSystemdDesign wantqtoqknowqmore? ridavidekfsd@gmail7com DavideyRizzo[yPhD fullqreferences http(]]bit7ly] FSD3_Rizzo_ref Opportunities for scaling up research on agricultural dynamics pppp Use–of–crop–sequences–for–databmining of–remotely–sensed–time–series across–multiple–scales Davide4RizzoS4 El4Ghali4Lazrak4¹4 Jean‐François4Mari4¹4²4 Laurence4Hubert‐Moy4³4 Marc4Benoît4² :sUMR4œè6q4HGIR74INRH‐INPT74Castanet‐Tolosan74FRH ¹ssINRA74SHD‐HSTER74Mirecourt74FRH ²ssLORIA74UMR4féVy4N4INRIH74Vandœuvre‐lès‐Nancy74FRH ³sLETG‐Rennes‐COSTEL74UMR4CNRS4péé64Université4de4Rennes4è74Rennes74FRH DbRizzobbEGbLazrakbbJFbMaribbLbHubert-MoybbMbBenoîtp dddddddDATA-MININGdMETHOD temporalb segmentation linearbmodel bbbbspatialb segmentation ergodicbmodel .allbstatesbareb interconnected5 model topology & hierarchy yyylandycoveryclassificationy qysequenceylengthy context4wisey approximationyofyGDy spaceyasysimpleychain space filling (fractal) curve visualisationb,binterpretation webbdynamicbinterfaceb[-7] agronomicd adaptation DATAdPREPARATION KNOWLEDGEd EXTRACTION landscapeysegmentation temporo4spatialyclasses Scalingyupy theyresearchyonyfarmingy systemsyfromyplot]farmytoy landscapeylevelywillymakeypossibleytoy buildyfarmingysystemydesignyfromyay landscapeqagronomyyperspectivey[C4–] 7 Thisyimpliesytoyimproveytheyunderstandingyofy theyrelationybetweenylandypatterns[yfarmingy practicesyandynaturalyresourcesy[H411] 7 Globaly statisticsyindicateyay stagnationyinytotalyyieldsy forymajorycrops7yFurthery improvementsyrequireyagronomistsy toyenhanceytheywaysytheyyaddressythey farmingyuseyofylandyandywatery[1] 7y Consideringytheylimitednessyofythesey resources[yimprovementsyofyfarmingy activitiesywouldydefinitelyybenefityfromy smarterqspatialqdesignyofycroppingyandy mixedycrop4livestockysystemsy[G[j] 7 hypothesisq observationyqy modellingyofyagriculturaly landycoverysequencesycany incorporateyfarmers’y medium4termy decision4makingy processes Landscapessegmentationsinto4patches4of4 land4cover4sequences4is4an4innovative4 approach4to4identify4land4management4units4 relating4farmers’4choices4and4natural4 resource4management34 Perspectives:sinforming4local4planners’4 decision‐making4with4spatially4explicit4 insights4about4farming4system4dynamics34 Hence74supporting4a4shared4landscape4design4 based4on4the4diversity4in4farming4systems34 YarpcasepstudyBbabwatershedbofbq-z8b km²b.BrittanyBbFrance5bwherebthebmainb cropsb–bmaizeBbwheatbandbgrasslandsb–b arebrelatedbtobindustrialbbreedingzb Ab-9–yearbtimebseriesb.-••C–922x5bofb satellitebimagesbwasbclassifiedbintobqblandb coverbclassesbforbindividualbfieldb polygonsBbthenbsampledbwithbab92mb regularbpointbgridzb This,approach,proved,its,applicability,at,different,scales, ranging,from,local,farming,systems,to,large,watershed,and, regional,areas,[16‐17] ., Further,implementations,are,being,developed,based,on,the, similar,principles:,first,,identification,of,sequences,,then, mapping,[3,18] . CONCLUSIONS inputqdatay–ysampledyony ayregularlyyspacedypointygridy –yareyscannedywithyayfractaly curveywhereyeachypointyholdsyay timeysequenceyofylandycovers7y stochasticqsegmentationy withyhierarchicalyHiddenyMarkovy Modelsy-HMMwywhoseyspatialystatesy areytemporalyHMMycapableyofy assigningyayprobabilityytoyaytimey sequencey[1G41j] 7 keypfeaturesp •pD15pAnalysisbofb timebregularitiesbofb landbcoverb sequencesbinsteadbofb individualblandbcoverb changeszb •pD25bContextbwiseb spatialbsegmentationz •bScalingbupbresearchbonbagriculturalbdynamicsb requiresbhetherogeneousbandbdetailedb databsourceszb bbbb •bAvailableblandbcoverbmapsbrarelybensureb continuitybinbtimeBbseamlessbcoveringbofblargeb areasbandbdetailedbcropbclassificationzb bbbb bb•bDatababoutbfarmingpmanagementbareb difficultbtobretrievebbecauseb ofbthebcontinuousb adaptationsbtobcomplexb drivingbfactorsbb[-0–-8]z •bExistingbdatasetsbprovideb promisingbbasesbtobreconstructb agriculturalblandbcoverb sequences4b French)TerUti,)Land)Parcel) Identification)System)(LPIS,) differently)available)throughout) Europe)) )))) •bAdvancesbinbremotepsensingb canbhelpbfacingbtheblackbofbdataBb althoughbtheblistbofbidentifiedb cropbtypesbshouldbbebimprovedz Reversingbthebclassicalb spacepdominantbapproachb.focusedb onblocalblandbcoverbchanges5btob overcomebthebinter–annualblocalb variabilitybofbcultivatedbcropszb bbbbbb Timepdominantpmodelingb frameworkbfostersbinsteadbab landscapebsegmentationbbasedbonb similarblandbcoverbsequencesb thusbmappingbspatialbunitsbofb .potentially5bsimilarbfarmingb practiceszb Webdistinguishedbpermanentb frombtemporarybgrasslandb andbidentifiedbandblocalizedb thebtypebofbrotationsbinbwhichb temporarypgrasslandsb werebinvolvedzb bbb •,Possible,hotspot,zones,at,the,origin, of,the,high,nitrogen,rates,observed,for, several,years,in,the,local,rivers., Althoughbinputbmapsb derivedbfrombremoteb sensingbwerebthematicallyblessb diversebthanbthosebderivedbfromb fieldbsurveysBbtime–spaceb segmentationbrevealedbsomeb interestingbspatialbdynamicsbofb landbcoverbsequenceszb Acevedof2011– Interdisciplinary– progress–in–food– production…–Environ– Conserv–,GÉSRS–JS fMorainefetfal]f2014 Farming–system–design–for– innovative…–Animal–GÉS.DB–SJ Murguefetfal]f2105 Toward–integrated–water–and– agricultural–land–management…–Land–Use– Policy–BRÉR.–’, Thenailfetfal]f2009 The–contribution–of–cropbrotation–organization…–Agric– Ecosyst–Environ–S,SÉ.DJ–SM Leenhardtfetfal]f2010 Describing–and–locating–cropping–systems…–Agron–Sustain–Dev–,DÉS,S–G BenoîtXfRizzofetfal]f2012 Landscape–agronomyÉ–a–new–field–for–addressing–agricultural–landscape–dynamicsz– Landsc–Ecol–SDÉS,GR–MB Boiffinfetfal]Xf2014 Agronomieh–espaceh–territoire…–Cah–Agric–.,ÉJ.–G, ScherrfsfMcNeelyf2008 Biodiversity–conservation–and–agricultural–sustainability…– Philos–Trans–R–Soc–B–Biol–Sci–,’,ÉBJJ–MB Rounsevellfetfal]f2012 Challenges–for–land–system–sciencez–Land–Use–Policy–.MÉGMM–MSD Schallerfetfal]f2012 Combining–farmers’–decision–rules–and–landscape…– Landsc–Ecol–.JÉB,,–B’ Rizzofetfal]f2013 Farming–systems–designing–landscapes…– Dan–J–Geogr–SS,ÉJS–G’ MarifsfLefBerf2006f Temporal–and–spatial–data–mining…– Soft–Comput–SDÉBD’–SB Marifetfal]f2013 Time–space–stochastic–modelling…–Environ–Model–Softw– B’É.SM–.J fLandaisfsfDeffontainesf1988 Les–pratiques–des–agriculteurs…– Études–Rural–SDMÉS.R–RG fDusseuxfetfal]f2011f Identification–of–grazed–and–mown–grasslands…–’th– Intz–Workshop–Analz–MultibTemporal–Remote–Sensz– Imagesh–ppz–SBR–G Mignoletfetfal]f2007 Spatial–dynamics–of–farming–practices–in–the–Seine– basin…–Sci–Total–Environ–,JRÉS,–,. Xiaofetfal]f2014 Modeling–the–spatial–distribution–of–crop– sequences…–Comput–Electron–Agric–SD.ÉRS–’, Duryfetfal]f2013 Croppingbplan–decisionbmaking–on–irrigated– crop–farms…–Eur–J–Agron–RDÉS–SD T7p.bScalingbupbfrombfarmbtoblandscapeb,b multiscalebscenariobanalysisbofbagriculturalbsystems download the poster http(]]bit7ly]FSD5_Rizzo_poster 2 page abstract http4AAbitzlyAFSD5_Rizzo_abstract Morepinformation:p LazrakbetbalzBb.submitted5b Mappingbagriculturalblandbuseb dynamicsbwithbremotelybsensedb series4babgenericbdatabminingb approachbatbabwatershedbscale Canqmapsqofqlandq coverqsequencesqimproveq cross-scalequnderstandingqofq farmingqsystems? aim toydiscussyay timeydominanty andycontextywisey data4miningy method [1] [2] [3] ffff [4] [5] fff [6] [7] fff [8] ffff [9] fff [10] [11] [12] [13] [14] [15] fff [16] [17] [18] challengesdddddddddddddddddddddddddddddddddddddopportunitiesddddddddddddddddddddddddmajordnovelty