Monitoring and Early Warning of Vector‐borne Diseases in  China by Earth Observation Data Mining (MWVDEODM)

Dr 3 project ID, 50515

C‐PIs: Prof Chuanrong

Li, Prof Xiaonong

Zhou E‐PI: Yaxin

Bi 

Outline• Project background • Objectives• Team composition• Scientific issues• Methodology

– Study area– Data acquisition– Analysis

methods

• Anticipated results• Training of young scientists • Project schedule

Project BackgroundSchistosome

血吸虫

Oncomelania钉螺

Mosquito蚊虫

Malaria/dengue疟疾/登革热

Zooplankton浮游动物

Leishmaniasis黑热病

Rat老鼠

Agiostrongyliasis管圆线虫

Water Temperature Humidity Vegetation ……

Oncomelania钉螺

Mosquito蚊虫

Sand Fly白蛉

Rat老鼠

Epidemic 

and 

infectious  

diseases

Vector

Environmental 

Factors

Many epidemic and infectious diseases are closely related to natural environment due to the presence, 

breeding and evolution of their pathogens or reservoir hosts, especially vector‐borne diseases (e.g. 

schistosomiasis, malaria and dengue, etc.) which rely heavily on their vectors.

Project Background

The traditional in-situ survey methods based on field detection are difficult to meet the demand of monitoring in large scale.

The traditional in-situ survey methods based on field detection are difficult to meet the demand of monitoring in large scale.

Monitoring characteristics of vectors’ spatial/temporal distribution is of vital importance to the prevention and control of vector-borne disease.

Monitoring characteristics of vectors’ spatial/temporal distribution is of vital importance to the prevention and control of vector-borne disease.

Remote sensing technology provides promising ways for snail monitoring and control.

Remote sensing technology provides promising ways for snail monitoring and control.

Project Background

Remote sensing experts may not exactly know what environmental factors are required to identify the incubators of vector-borne diseases.

Effective RS data processing and parameters retrieval techniques are also challenges for hygiene experts who are lack of experience of remote sensing applications.

Taking into account of different type of massive data are involved, computing scientists with substantial intelligent data analysis expertise is crucial to successfully incorporate advance intelligent data analysis, such as data mining, pattern analysis.

RS

Hygiene DM

Consequently, any single of these disciplines is insufficient, it is essential to bring together scientists from computing science and remote sensing along with domain experts to foster a substantial collaboration.

Consequently, any single of these disciplines is insufficient, it is essential to bring together scientists from computing science and remote sensing along with domain experts to foster a substantial collaboration.

Trans‐dis

ciplinary

Investiga

tion

ObjectivesBased on the research achievements gained during the Dragon 2 

and the requirements from monitoring and early‐warning of  epidemic diseases, the project aims 

To apply advanced remote sensing and computing technologies  into monitoring and early warning of vector‐borne diseases, 

with emphasis on:

•Joint research with remote sensing and hygiene experts, at the  support of GIS and computer technologies 

•Exploitation of various remote sensing data from newly  launched EU and Chinese satellites (e.g., Sentinel, CBERS‐03, 

Beijing‐2, HJ‐1‐C)

Team Composition

11Academy of Opto- Electronics, Chinese Academy of Sciences

33University of Ulster, United Kingdoms

22National Institute of Parasitic Diseases, Chinese Center for

Diseases Control and Prevention

• A joint research with experts from different areas

Trans‐

disciplinary

Team

Team Composition

• Prof Chuan‐rong

Li, Academy of Opto‐Electronics, Chinese  Academy of Sciences. 

– Characterizing environmental factors using remote sensing  technologies   

• Prof Xiao‐nong

Zhou, National Institute of Parasitic Diseases,  Chinese Center

for Diseases Control and Prevention.

– Field survey data collection and domain knowledge acquisition

• Dr Ya‐xin

Bi, University of Ulster, United Kingdoms– Data mining, pattern analysis and data fusion for satellite data

exploitation

Team Composition

• Prof. Ling‐li

TANG (AOE‐CAS, China)

• Dr. Ling‐ling MA (AOE‐CAS, China)

• Dr. Yuan‐yuan

JIA (AOE‐CAS, China)

• Dr. Yong‐sheng

ZHOU (AOE‐CAS, China) 

• Dr. Yong‐gang QIAN (AOE‐CAS, China) 

• Dr. Zhao‐yan

LIU (AOE‐CAS, China) 

• Dr. Shi‐zhu

LI (NIPD‐CCDC, China)

• Dr. Guo‐jing

YANG (JIPD‐

CCDC, China) 

• Dr Shengli

Wu (Ulster, UK)

• Prof. Chris NUGENT (Ulster, UK) 

• Miss Jing

Liao

(Ulster, UK)

• ……

Scientific Issues‐1• Reveal environmental factors which have significant influences on the breeding of 

epidemic disease vectors by remote sensing experts and health experts

The environmental factors that

influence epidemic disease/ vectors

The environmental factors retrieved by remote sensing data

Biological Experiment

Earth Observation

Hygiene experts 

Remote sensing experts 

Scientific Issues‐2• Develop effective retrieval methods of environmental factors by multi‐source, 

especially new satellite remote sensing data (e.g., Sentinel2, Sentinel3, CBERS‐03, 

Beijing‐2, HJ‐1‐C)

Land use

Soil moisture

Temperature

……Vegetation cover

……

PROBASentinel

HJ‐1‐C ALOS

Scientific Issues‐3• Explore the driving mechanism and assimilating methods of temporal process 

model, and thus implement the identification and early‐warning of epidemic 

disease areas, e.g., Schistosomiasis, Malaria,

Dengue,

Leishmaniasis,

Agiostrongyliasis.

initialization 

RS data driving mechanism

Data Assimilation t0 tn

prediction

Re-

initialization

Tempora l process

model

prediction

Re-

initialization

Tempora l process

model

prediction

……

……

Prediction&

early-warning

Scientific Issues‐4• Develop temporal‐spatial distributed models of the epidemic/infectious diseases by 

data mining, which reflect the relation among environmental factors, diseases 

vectors, infectious diseases

Vectors

… …soil

Infectious diseases

Environmental factors

data mining techniques

Methodology‐Study

area

Schistosome

Malaria

Degue

Leishmaniasis

Agiostrongyliasis

Methodology‐Satellite

data acquisition Environmental 

factors  Satellite data EO  data  sources

Surface 

temperature

FY‐2C VISSR, FY‐3 MWTS Chinese EO data

ATSR data of ERS 1&2,AATSR data of ENVISAT,Sentinel‐3 A‐B ESA EO data

Terrain feature

HJ‐1C S‐bandChinese EO data

Sentinels C‐band, CRYOSAT‐2 ESA EO data

ALOS PALSAR&PRISM ESA TPM EO data

Soil moisture ENVISAT ASAR, SMOS MIRAR ESA EO data

Vegetation index 

and land cover

Beijing‐1 & 2, HJ‐1A/‐1B, FY‐3 Chinese EO data

Sentinels HRC,  ESA EO data

ALOS AVNIR‐2, Multi‐angle CHRIS data of PROBA ESA TPM EO data

Wind speed and 

wind profile 

products

FY‐2C VISSR Chinese EO data

ALADIN of ADM‐Aeolus,RA‐2 data of ENVISAT,RA of ERS ESA EO data

Methodology‐Analysis methods

Anticipated results• Development of the joint parameters inversion algorithm with different 

scale optical and microwave remotely sensed data, and obtain main  parameters of disease monitoring;

• Establishment of the remote sensing monitoring model of vectors;

• Establishment of a spatio‐temporal distribution of vector‐borne diseases  and spatio‐temporal model of transmission of vector‐borne diseases;

• Development of the application studies on typical cases of vector‐borne  diseases

• Development of a prototype of spatio‐temporal monitoring methods of  vectors;

• Training a group of youth scientists with interdisciplinary knowledge and  enhance the capacity of monitoring vector‐borne diseases.

Training for youth scientists• To address the current skills shortage in this multidisciplinary

area, a training programme for youth scientists in the theory  and practice, include as follows:

– Co‐supervision of PhD and MSc students

– Provide short courses for the members of the DRAGON 3 programme in  Characterise Environmental Features by Remote Sensing, Pattern 

Analysis/Data Mining, Disease‐vector Detection   

– Provide workshops for result dissemination 

– Provision of summer schools and postgraduate courses for the Dragon  3 partners 

2012.7

Project schedule

• 1st year (2012.07‐2013.06)– Carry out the literature review, collect and collate remote sensing and ground data, and 

complete pre‐processing along with preliminary studies 

• 2nd year (2013.07‐2014.06)– Realize remote sensing parameters of vector‐borne diseases based on the analysis of 

biological characteristics 

– Develop parameter inversion algorithm with different scale optical, microwave remotely 

sensed data, according to the monitoring needs of vector‐borne diseases’s vectors

– Use machine learning and data mining techniques to build remote sensing tempo‐spatial 

monitoring model of vector‐borne diseases’

vectors

2013.6 2014.6

Project schedule (cont’d)

• 3rd year (2014.07‐2015.06)– Analyze the tempo‐spatial relation between vector‐borne diseases and environmental 

factors

– Build a tempo‐spatial transmission model for vector‐borne diseases

– Develop monitoring and early warning systems through implementing all the developed 

algorithms 

• 4th year (2015.07‐2016.06)– Carry out case studies and evaluation of the models: the remote sensing monitoring 

model of vector‐borne disease vectors; 

– Carry out case studies and evaluation of the models: the tempo‐spatial transmitting 

model for vector‐borne diseases

– Optimize the remote sensing monitoring model of vector‐borne diseases’

vectors and the 

tempo‐spatial transmitting model of vector‐borne diseases

2014.7 2015.6 2016.6

Thank You!