Data mining techniques on satellite images for discovery of risk areas

Abstract

The high rates of choiera epidemic mortality in Jess developed countries is a challenge for health facilities to which it is necessary to equip itself with the epidemiological surveillance. To strengthen the capacity of epidemiological surveillance, this paper focuses on remote sensing satellite data processing using data mining methods to discover risk areas of the epidemic disease by connecting the environment, climate and health. These satellite data are combined with field data collected during the same set of periods in order to explain and deduct the causes of the epidemic evolution from one period to another in relation to the environment. The existing technical (algorithms) for processing satellite images are mature and efficient, so the challenge today is to provide the most suitable means allowing the best interpretation of obtained results. For that, we focus on supervised classification algorithm to process a set of satellite images from the same area but on different periods. A nove! research methodology (describing pre-treatment, data mining, and post-treatment) is proposed to ensure suitable means for transforming data, generating information and extracting knowledge. This methodology consists of six phases: (1.A) Acquisition of information from the field about epidemic, (1.B) Satellite data acquisition, (2) Selection and transformation of data (Data derived from images), (3) Remote sensing measurements, (4) Discretization of data, (5) Data treatment, and (6) lnterpretation of results. The main contributions of the paper are: to establish the nature of links between the environment and the epidemic, and to highlight those risky environments when the public awareness of the problem and the prevention policies are absolutely necessary for mitigation of the propagation and emergence of the epidemic. This will allow national govemments, local authorities and the public health officiais to effective management according to risk areas. The case study concems the knowledge discovery in databases related to risk areas of the choiera epidemic in Mopti region, Mali (West Africa). The results generate from data mining association mies indicate that the level of the Niger River in the wintering periods and some societal factors have an impact on the variation of choiera epidemic rate in Mopti town. More the river level is high, at 66% the rate of contamination is high.

Big Data and Climate Change

“…It has been systematically reviewed in [99] of the big data analytics in global infectious disease surveillance, whilst its corresponding big data applications related to climate science still stay in their early stage of development. Traore et al [100] applied data mining techniques on satellite imagery data for identifying risk areas that are exposed to epidemic crisis. Similarly, Manogaran and Lopez [101] focused on dengue and proposed a big climate data based surveillance system for continuous monitoring and timely warning.…”

Recurrent Cholera Outbreaks in Sub-Saharan Africa: Moving beyond Epidemiology to Understand the Environmental Reservoirs and Drivers

“…A previous study mined data from social media and news outlets to estimate the dynamics of the 2010 cholera outbreak in Haiti [60]. In Mali, data mining was used to process satellite data for the identification of risk areas of cholera [61]. The application of these emerging research tools will provide additional insights into cholera dynamics, beyond those provided by the current conventional research methods.…”

Deep convolution neural network for image recognition

“…The recent development of intelligent data analysis methods brings new opportunities and challenges for a wide variety of scientific problems including risk management and image analysis. In previous works (Traore et al, 2017), we applied data mining techniques on satellite images for the discovery of risk areas in Tele-epidemiology. Teleepidemiology is the study of the propagation of human or animal diseases, transmitted by water, air or vectors that are related to climatic, meteorological and environmental factors, using information and communication technologies (Marechal et al, 2008;Traore et al, 2016).…”

“…The results generated from the association rules indicate that the level of the Niger River in the wintering periods and some societal factors have an impact on the variation of cholera epidemic rate in Mopti town. More the river level is high, at 66% rate of contamination is high (Traore et al, 2017). It has been established the nature of links between the environment and the epidemic, and to highlight those risky environments when the public awareness of the problem and the prevention policies are absolutely necessary for mitigation of the propagation and emergence of the epidemic situations.…”