Mobile Information System for Species Localization

and Modelling Applied to the Amazon Forest

Álvaro Silva

1,2

, Marcelo Queiroz Leite

and Pedro Luiz Pizzigatti Corrêa

Nokia Institute of Technology (INdT)

Av. Torquato Tapajós, 7200, Col. Terra Nova, Manaus, Brazil

PCS, Escola Politécnica, Universidade de São Paulo (USP)

Av. Prof. Luciano Gualberto, São Paulo, Brazil

Abstract. Species distribution modelling based on ecological niche uses data

collected in the field by researchers which indicates whether a particular species

is present or absent. However, without reliability or accuracy, the generated

models are inaccurate. Because of this we propose a system which uses a smart

phone and a service oriented approach to data collection. Using this, a

researcher can submit data collection points for processing on remote servers

which will return the distribution model after it has been previewed. It

automates the collection and modelling process and allows collaboration

between the researchers, but the system needs to be designed giving some

considerations to the often hostile local environment in which it will operate –

the Amazon Forest. This paper presents the benefits of using SOA (Service

Oriented Architecture) to model this kind of system.

1 Introduction

Species distribution based on ecological niche modelling has been used in several

areas of ecology. It uses mathematics techniques which are applied to weather

statistics and other physical factors which can affect the geographic extension of the

species in its ecological niche [1].

So with the known localization data (or absence) of occurrences of individuals

species and relating them to environmental variables (such as relief, climate,

humidity, etc) it is possible to predict the probability that a region will be favourable

to survival of that species.

This process depends on the quality of the data collected in the field. [2] Presents

research concerning the influence of errors in the collection point position. There are,

however, human factors that can also influence the quality of these points.

This paper presents a mobile system which supports the collecting and modelling

of data for the distribution of ecological niche. It also evaluates how mobile devices

can influence the quality of data collected in terms of security, integration, storage

and availability. Beyond this, it proposes a novel approach to help scientists choose an

area in which to collect field data by previewing the models available to the

researcher.

Silva Ã ˛A., Leite M. and Correa P.

Mobile Information System for Species Localization and Modelling Applied to the Amazon Forest.

DOI: 10.5220/0003029301010108

In Proceedings of the International Joint Workshop on Technologies for Context-Aware Business Process Management, Advanced Enterprise Architecture and Repositories and Recent

Trends in SOA Based Information Systems (ICEIS 2010), page

ISBN: 978-989-8425-09-6

2 Distribution Species Modelling

Distribution species modelling is a way of analyzing data which is applied mainly in

biology which uses advanced systems of geographic information [3].

To understand what this modelling represents it is necessary to understand the

concept of ecological niche: according to [4] ecological niche is defined as “a space

with n-dimensional volume where each dimension represents the interval of

environmental conditions or necessary sources for the species survival and

reproduction”.

In [3], ecological niche is defined as a group of ecological condition in which a

species is capable of maintaining population without immigration.

According to these concepts the ecological niche is nothing more than a

determined region where the group of factors favours the species survival.

Environmental features that influence species survival can be temperature, humidity,

salinity, pH, feeding sources, luminous intensity, predatory pressure, population

density, among others. Environmental factors are limited and remain relatively

constant on the interval related to the timeline of these animals [5].

The ecological niche is divided between function and performance. Functional

niche is defined as a group of environmental conditions necessary for a species

survival without considering the influence of predators. Performance niche is where

the species really occurs [6]. You can say that performance niche is a sub-group of

functional one.

Predictive modelling of species distribution is mainly concerned with the

ecological niche modelling. It proposes a solution based on artificial intelligence for

foreseeing a probable geographic distribution of species.

The distribution modelling of ecological niche plays an important role in ecology.

Among the main application are planning for environmental preservation areas [7],

[8], [9]. Choosing a preservation area requires knowledge about a species ecological

niche. With predictive modelling it is possible to identify statistically these areas.

Another area in which modelling is a driving force is in climate change research

[10], [11] which aims to identify how living creatures are affected by global warming.

Other applications can also be found: species replacement in nature, management

of species and habitat, biogeography and others [8].

3 Species Distribution Mobile System

Below we present some features of the proposed system. The case study of the system

has been performed in Amazonas state in partnership with National Institute for

researches of Amazon (INPA) [12].

3.1 The System Importance

The usage of mobile phones for performing data collection offers the following

benefits to the collecting and modelling of ecological niche distribution:

102

 Collection automation: A user need only select a button in the geographic

interface to identify a point of presence or absence of a species. Automatically,

the system calculates geographic coordination through GPS (Global Positioning

System) and stores that data. The user will not have to take notes in other

sources or electronic spreadsheet. This also guarantees reliability of the

collected data.

 Accompanying changes in the model: With this system it is possible to

follow the mobile phone through the evolution of the model to the extent that

more data can be added, including data from other field researchers.

 Better use of a researcher’s distribution: With the simplification of the

system more areas can be analyzed by the researchers. The researcher can work

looking for species in different areas and still can transfer data for all other

researchers to access.

 Convenience: The mobile device is more compact thereby reducing the

number of devices necessary to conduct the research.

 Usability: A more friendly and intuitive interface will be proposed in this

document. With this system the user will gain some other facilities for

performing data collection such as selecting only one button on the graphic

interface to identify the presence or absence of species.

 Faster GPS in regions with GSM (Global System for Mobile

Communications) networks: Modern phones do not use the traditional geo

positioning system, but the Assisted GPS (A-GPS). It is a system that uses a

server for helping to minimize the Time To First Fix (TTFF) and improving the

robustness of the positioning. The accuracy of location is less than 3.1 meters

and the TTFF are less than 5 seconds, working even in situation of critical

satellite signs [13]. The A-GPS uses any available networks such as the GSM

network of the operator or even a wireless network in urban areas. This type of

technology use case is important for the modelling of species which live in

urban environments, such as rats and mosquitoes for example, when identifying

possible diseases routs [14].

3.2 Technical Restrictions

There are two main technical restrictions for the proposed system. They are:

 Network availability: One of the biggest challenges this project faces is the

issue of communication between the cellular and the service provider. Most

use cases for a system such as this involve communication networks with

intermittent network access so the system shall work most of the time in off-

line mode. The main objective of the application is in automating the data

collected and its sending to the server. However it is not intended that data

collection occurs at the point of collection but as soon as there is an available

network. Working in off-line mode the application will be able to store the

current coordinates, show saved models and analyze these models.

 Processing power of the devices: The predictive modelling of the species

distribution requires high performance computing [14] the generation of a

model can take between hours and days to prepare.

103

3.3 Business Restriction

This type of research in Brazil needs to comply to some rules concerning the transfer

of biodiversity data. This data needs, in many cases, to be kept secret. These measures

are necessary for environmental property protection.

This kind of concern is important for Brazil once which has 20% of the total

number of species on the planet. In august of 2009 the Ministry of Science and

Technology published 'the concierge 693’ which standardizes the manipulation and

distribution of research data about biodiversity. This concierge makes the following

observations:

 The management and authorship of data must be published.

 The usage condition and the access to data must be protected in the database.

3.4 Usability

The system needs to have easy browsing, be intuitive and have few steps necessary

for performing tasks. The kind of device that is being proposed for use is a Smart

phone, which has a limited screen size. That means that the icons need to be arranged

in such to be very easy to use. Fig. 1 shows the screen of the main menu of this tool in

a mobile device.

Fig. 1. Main Menu in a mobile device demonstrating the usability with the thumbs.

This interface shows how efficient it is for small devices that have touch screens.

Usage of the thumbs allows for a more comfortable experience. Fig. 2 shows the

flowchart of initial activities with skeleton of the screens.

104

Fig. 2. Flowchart for some screens of the system.

4 SOA to Mobile Species Distribution Modelling

SOA was chosen as the distribution mechanism due to the challenge of having access

to a distribution model via mobile phones. Using this system the following use cases

were identified as services and offered by the providers:

• Environmental data provider;

• Maps provider;

• Species data provider;

• Modeling algorithms provider;

• Pre-modeling algorithms provider;

• Post-analysis algorithms provider.

At Fig. 3 is shown the architecture proposed by this paper.

Basically, an infra-structure with a set of servers is used. Each of the offered

services can be available in different servers. The mobile devices will have access to

these services at the moment they are in regions with Internet access, having Wi-fi,

GSM or any other kind of connection. Most of the collected data happen in remote

regions, without this kind of infra-structure. For this reason, the system runs in two

working modes: connection with or connectionless. The connection with mode is used

for transferring data between the mobile devices and the service providers. While the

connectionless mode is used mainly while the researcher in field looking for points of

species presences or absences. In this mode the data persists on the device.

Before the data can be transferred, the information is first checked by an active

service on the device itself, this service aims to perform a pre-processing of

information in order to ensure the integrity of data being made available to other

modules. If the information is not corrupted, it is transmitted through a provider of

105

Fig. 3. Services used for species distribution modelling.

communication services to an intermediate server. If the device is operating off-line

this information is stored on the device itself, until it has access to any network. To

receive the information collected by the device, the intermediary service provider is

engaged to provide this content to a number of providers of services, each with a

separate responsibility within the architecture, so that at the end of execution this data

can be made available to a service provider responsible for ensuring the persistence of

information processed in a server database.

Through the use of services, the SOA model provided the project a coherent

distribution of resources in infrastructure. Despite the technical constraints (section

3.2) the use of the Internet has provided an efficient way to transfer the data collected

with the service providers in a quick and dynamic manner.

This service oriented architecture allowed us to solve the following issues:

• High performance computation on a mobile phone: Although mobile phones

do not have enough capabilities to perform distribution modelling, it was

possible to show a model on the device due to the use of services.

• 6yReuse of existing services to composition of many solutions: Some services

used on this project are from the Openmodeller project and others from

SpeciesLink. They obtain from the services models and data concerning the

presence or absence of a species.

• Use of web services to provide fast software updates: With this approach each

research team is able to get the current data that all other teams have collected.

Without this system the update can only be done after the team come back to

the base. Another feature of this project is the ability to do upgrades on the

software.

106

5 Conclusions

The system proposed in this paper allows a user to preview the distribution models of

ecological niche using a low computational power mobile device. It was verified that

mobile devices are powerful enough to make previewing the model possible, given

the service orientated system architecture. It was even possible using communication

with remote servers.

We also show that an opportunity exists for data collection given a crowd sourcing

approach

The automation of data collecting through a mobile device is important as it

reduces human intervention in a system. Further research is necessary to measure the

quantity and quality of the collected data with this system.

The service oriented architecture shows that it is efficient in this type of project.

Modelling species distribution in a distributed manner through the use of services in

different servers is an interesting use case for Service Oriented Computing.

References

1. Soberón, J. & Peterson, A.T., 2005. Interpretation of models of fundamental ecological

niches and species' distributional areas. p.10.

2. Iwashita, F., 2008. Sensibilidade de modelos de distribuição de espécies a erros de

posicionamento de dados de coleta. Instituto Nacional de pesquisas espaciais.

3. Peterson, A.T., 2001. Predicting species geographic distributions based on ecological niche

modeling. Cooper Ornithological Society.

4. Hutchinson, G.E., 1957. Concluding remarks. Cold Spring Harbor Symposia on

Quantitative Biology, pp.415-27.

5. Bazzaz, F.A., 1998. Plants in changing environments: Linking physiological population, am

community ecology. Am community ecology.

6. Malanson, G.P., Westman, W.E. & Yan, Y.-L., 1992. Realized versus fundamental niche

functions in a model of chaparral response to climatic change. Ecological Modelling,

pp.261-77.

7. Austin, M.P., 2002. Spatial prediction of species distribuition: an interface between

ecological theory and statistical modelling. Ecological modelling Elsevier, pp.101-18.

8. Guisan, A. & Zimmermann, N.E., 2000. Predictive habitat distribution models in ecology.

Ecological modeling, pp.147-86.

9. Sohn, N., 2009. Distribuição provável, uso de hábitat e estimativas populacionais do galo-

da-serra (Rupicola rupicola) com recomendações para sua conservação. Universidade

Federal do Amazonas.

10. Peterson, A.T. et al., 2001. Effects of global climage change on geographic distributions of

Mexican Cracidae. Ecological modelling, pp.21-30.

11. Canhos, V. et al., 2005. A framework for species distribution modeling. Research project.

São Paulo: Reference Center in Ambiental Informatics, USP Polytechnic School, National

Institute of Spacial Research.

12. INPA, (2010). Instituto Nacional de Pesquisas da Amazônia. Retrieved September 1, 2009,

from http://www.inpa.gov.br.

13. SCHREINER, K., 2007. Where We At? Mobile Phones Bring GPS to the Masses. IEEE

Computer Graphics and Applications, 27, pp.6-11.

14. Santana, F.S., Siqueira, M.F., Saraiva, A.M. & Correa, P.L.P., 2008. A reference business

process for ecological niche modelling. Ecological informatics 3, pp.75-86.

107