Content uploaded by Leonardo Talero
Author content
All content in this area was uploaded by Leonardo Talero on Sep 06, 2023
Content may be subject to copyright.
Developing a Mathematical Programming Model for a Decision
Support System in Theobroma Cacao Production
A Human-Computer Interaction Perspective
Leonardo Talero-Sarmiento†Henry Lamos-Diaz
Ingeniería Industrial – Doctorado Ingeniería Industrial
en Ingeniería Universidad Industrial de
Universidad Autonoma de Santander
Bucaramanga Bucaramanga
Bucaramanga, Santander, Bucaramanga, Santander,
Colombia Colombia
ltalero@unab.edu.co hlamos@uis.edu.co
ABSTRACT
This paper outlines the research objectives, methodology, and
preliminary findings of a doctoral study entitled “An optimization
model for Theobroma Cacao yield maximization based on smart
farming technologies”. Considering smallholder farm
characteristics, agribusiness, and agronomists, the dissertation
aims to positively enhance cocoa productivity supported by a
Decision Support System (DSS) and smart farming technologies
applied to Theobroma Cacao production impacting the production
link of the chocolate food supply.
CCS CONCEPTS
• Stochastic control and optimization • User centered design
Machine learning theory • Data mining
KEYWORDS
Human-Computer Interaction, Decision Support System,
Theobroma Cacao, Smart Farming Technologies, Mathematical
Programming Model, Data Mining.
1 Introduction
The overarching goal of this research encompasses three
interrelated objectives aimed at enhancing the productivity of
Theobroma Cacao, commonly known as the cocoa tree, an
essential crop whose yield significantly impacts the global
economy and the livelihoods of local farming communities.
The first phase of this research is to identify the variables that
affect Theobroma Cacao's productivity. This process involves
applying sophisticated Data Mining techniques to uncover
patterns, correlations, and trends that may influence crop yield. By
harnessing the power of these techniques, this research aims to
elucidate a nuanced understanding of factors contributing to the
productivity of Theobroma Cacao, ranging from environmental
conditions to cultivation practices, e.g., irrigation [1], fertilization
[2], pruning[3], shading [4], and genetic variety [5].
The second phase is to develop a mathematical programming
model for maximizing Theobroma Cacao yield, including the data
mining insights as model parameters. The model optimizes
biomass density by considering various factors related to cocoa
farming [6] and good agricultural practices [7]. The research
proposes a two-stage stochastic model [8]–[10] to consider the
variability of environmental parameters during pod growth. The
model solution includes model decomposition techniques [11] to
solve the large-scale problem.
The third and final phase is to create a decision support system
(DSS) incorporating smart farming technologies. By integrating
these technologies into a DSS, we aim to equip farmers with a
sophisticated tool that can aid in making informed decisions about
their farming practices [12]. In this research: Irrigation and
Draining treatments. This tool would consider each farm
situation's unique characteristics, enabling a highly personalized
approach to agricultural decision-making.
Collectively, these objectives present an innovative approach to
enhancing Theobroma Cacao's productivity, integrating water
management decisions as productivity enablers. The anticipated
outcome is a comprehensive, technologically advanced system
that can support farmers in their quest for increased productivity.
2 Methodology
Phase one: The cocoa productivity assessment, leveraging
Knowledge Discovery in Databases [13] with data sourced from
sensor networks or government bureaus' repositories [14], [15].
Phase two: Develop a mathematical programming model,
applying the steps to construct, solve, and implement the
stochastic model to consider the variability of environmental
conditions. This phase includes scenario simulation and scenario
180
INTERACCION 2023, Sept 2023, Lleida, Catalonia Spain
reduction to create a well-defined and deterministic equivalent
problem. Phase three: The deployment of a Smart Farming
Solution, applying the System Development Lifecycle [16] and an
Interaction Design Lifecycle model [17] to determine system
requirements, user characteristics, tasks, and contexts of use of the
tools.
3 Preliminary Findings
The preliminary findings reveal a dichotomy between smallholder
farmers and agribusinesses, with agribusinesses showing higher
technology readiness [18]. Data gathering will require either
internet download from the NASA POWER database or in situ
censoring, each with unique challenges. The project assembled a
research team to tackle these challenges.
Figure 1: Roles of the design team
This project's significant contribution to HCI is the inclusion of
the Agronomist as a potential user of the DSS, who can support
farmers or farmer associations. This research aims to facilitate the
review and synthesis of relevant information during decision-
making related to good agricultural practices and identify a
common language for farmers based on the experience of
agronomists. This research proposal sets its sights on crafting a
mathematical optimization model for cocoa cultivation in
Santander. However, the authors anticipate the results to extend
beyond this specific context, potentially applying to other crops
and users. Our approach aims to spotlight key stakeholders, delve
into technological hurdles, and underscore the need for a
collaborative and multidisciplinary approach to this work.
5 Discussion
This doctoral study will confront Theobroma Cacao production
challenges by crafting a mathematical model for a Decision
Support System (DSS) to optimize production considering water
management. The paper outlined preliminary findings,
L. Talero-Sarmiento et al.
methodology, and future directions. The prospective influence on
Human-Computer Interaction (HCI) appears promising and has
the potential to extend the outcomes to broader applications.
ACKNOWLEDGMENTS
The authors are grateful to the Universidad Autonoma de
Bucaramanga and its Ph.D. in Engineering program (Red Mutis)
for providing the data access for this study. The Colombian
Bureau of Science (MinCiencias) has fully funded this research.
REFERENCES
[1] M. K. V. Carr and G. Lockwood, ‘The water relations and irrigation
requirements of Cocoa ( Theobroma Cacao L.): A Review’, Exp Agric,
vol. 47, no. 4, pp. 653–676, Oct. 2011, doi:
10.1017/S0014479711000421.
[2] G. Danso-Abbeam and L. J. S. Baiyegunhi, ‘Does fertiliser use improve
household welfare? Evidence from Ghana’s cocoa industry’, Dev Pract,
vol. 29, no. 2, pp. 170–182, Feb. 2019, doi:
10.1080/09614524.2018.1526887.
[3] D. H. Meneses-Buitrago, M. M. Bolaños-Benavides, L. F. Gómez-Gil,
and H. S. Ramos-Zambrano, ‘Evaluation of irrigation and pruning on the
phenology and yield of Theobroma cacao L.’, Agronomía
Mesoamericana, pp. 681–693, Aug. 2019, doi:
10.15517/am.v30i3.36307.
[4] I. B. Famuwagun, S. O. Agele, and O. P. Aiyelari, ‘Shade Effects on
Growth and Development of Cacao Following Two Years of Continuous
Dry Season Irrigation’, International Journal of Fruit Science, vol. 18,
no. 2, pp. 153–176, Apr. 2018, doi: 10.1080/15538362.2017.1416326.
[5] L. R. M. Pinto, S. D. V. M. Silva, and M. M. Yamada, ‘Evaluation of
phenotypic stability of resistance to Phytophthora spp. in cacao clones’,
Fitopatol Bras, vol. 32, no. 6, pp. 453–457, 2007, doi: 10.1590/S0100-
41582007000600001.
[6] C. Zhao et al., ‘A SIMPLE crop model’, European Journal of Agronomy,
vol. 104, pp. 97–106, Mar. 2019, doi: 10.1016/j.eja.2019.01.009.
[7] A. Tosto, A. Morales, E. Rahn, J. B. Evers, P. A. Zuidema, and N. P. R.
Anten, ‘Simulating cocoa production: A review of modelling approaches
and gaps’, Agricultural Systems, vol. 206. 2023. doi:
10.1016/j.agsy.2023.103614.
[8] J. L. Higle and S. Sen, ‘Two Stage Stochastic Linear Programs’, in
Stochastic Decomposition. Nonconvex Optimization and Its Applications,
8th ed.Boston, MA, 1996, pp. 1–33. doi: 10.1007/978-1-4615-4115-8_1.
[9] J. R. Birge and F. Louveaux, Introduction to Stochastic Programming. in
Springer Series in Operations Research and Financial Engineering. New
York, NY: Springer New York, 2011. doi: 10.1007/978-1-4614-0237-4.
[10] A. Shapiro, D. Dentcheva, and A. Ruszczyński, Lectures on Stochastic
Programming, 1st ed. Philadelphia: Society for Industrial and Applied
Mathematics, 2009. doi: 10.1137/1.9780898718751.
[11] R. Rahmaniani, T. G. Crainic, M. Gendreau, and W. Rei, ‘The Benders
decomposition algorithm: A literature review’, Eur J Oper Res, vol. 259,
no. 3, pp. 801–817, Jun. 2017, doi: 10.1016/j.ejor.2016.12.005.
[12] H. Azadi et al., ‘Rethinking resilient agriculture: From Climate-Smart
Agriculture to Vulnerable-Smart Agriculture’, J Clean Prod, vol. 319, p.
128602, Oct. 2021, doi: 10.1016/J.JCLEPRO.2021.128602.
[13] G. Piatetsky-Shapiro, Knowledge Discovery in Databases, 1st ed.
American Association for Artificial Intelligence, 1991.
[14] NASA, ‘The Power Project’, NASA Prediction Of Worldwide Energy
Resources, 2022. https://power.larc.nasa.gov/ (accessed Aug. 22, 2022).
[15] Ministerio de Agricultura y Desarrollo Rural, ‘AgroNet’, Red de
información y comunicación del sector Agropecuario Colombiano, 2021.
[16] I. F. Alexander and N. Maiden, Scenarios, stories, use cases: through the
systems development lifecycle. John Wiley \& Sons, 2005.
[17] H. Sharp, J. Preece, and Y. Rogers, Interaction Design: Beyond Human-
Computer Interaction, 5th ed. Indianapolis: John Wilei & Sons Inc.,
2019.
[18] A. T. Balafoutis, F. K. Van Evert, and S. Fountas, ‘Smart Farming
Technology Trends: Economic and Environmental Effects, Labor Impact,
and Adoption Readiness’, Agronomy, vol. 10, no. 5, p. 743, May 2020,
doi: 10.3390/agronomy10050743.
181