Conference PaperPDF Available

Developing a Mathematical Programming Model for a Decision Support System in Theobroma Cacao Production: A Human-Computer Interaction Perspective

Authors:

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.
Developing a Mathematical Programming Model for a Decision
Support System in Theobroma Cacao Production
A Human-Computer Interaction Perspective
Leonardo Talero-SarmientoHenry 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
ResearchGate has not been able to resolve any citations for this publication.
Article
Full-text available
CONTEXT Cocoa is an important commodity crop and source of income for millions of small-holder farmers. Nonetheless, questions on cocoa tree functioning, best management practices and climate change responses remain. Modelling is a powerful tool to address these questions, complementing experimental work that is expensive and time consuming due to the long productive cycle of the cocoa system. However, compared to other crops, cocoa modelling has not received as much attention. OBJECTIVE: We reviewed existing cocoa models and identified the main gaps in the literature and possible strategies to advance models of cocoa production. METHODS We first classified relevant research questions in cocoa production along three main axes (fundamental-applied, spatial organization, prediction horizon) and aligned modelling approaches along these. We then reviewed six published cocoa models using these axes as framework. This comparison revealed several modelling gaps for which we provide an overview of data availability for future model development. RESULTS (i) Several plant processes (i.e., water stress responses, respiration, climate change responses, nutrient effects and phenology) are either missing from existing cocoa models or are simulated based on general plant physiological knowledge rather than cocoa-specific knowledge. (ii) The only currently existing 3D model of cocoa architecture has very limited scope and does not include physiological processes. (iii) There are no model-based decision support tools available for supporting the main management practices such as irrigation, fertilization and pruning. (iv) Data for model calibration and validation are often scarce. CONCLUSIONS We conclude that data availability for model design, calibration and validation is currently the main bottleneck for further development of cocoa models. Extensive cooperation within the cocoa research community and a large network of long-term experiments under different climatic and management conditions are required to close the identified modelling gaps.
Article
Full-text available
Climate-Smart Agriculture (CSA) is seeking to overcome the food security problem and develop rural livelihoods while minimizing negative impacts on the environment. However, when such synergies exist, the situation of small-scale farmers is often overlooked, and they are unable to implement new practices and technologies. Therefore, the main aim of this study is to improve CSA by adding the neglected but very important element “small-scale farmer”, and introduce Vulnerable-Smart Agriculture (VSA) as a complete version of CSA. VSA indicates, based on the results of this study, that none of the decisions made by policymakers can be realistic and functional as long as the voice of the farmers influenced by their decisions is not heard. Therefore, to identify different levels for possible interventions and develop VSA monitoring indicators, a new conceptual framework needs to be developed. This study proposed such a framework consisting of five elements: prediction of critical incidents by farmers, measuring the consequences of incidents, identifying farmers' coping strategies, assessing farmers' livelihood capital when facing an incident, and adapting to climate incidents. The primary focus of this study is on farmers’ learning and operational preparation to deal with tension and disasters at farm level. Understanding the implications of threats from climate change and the recognition of coping mechanisms will contribute to an increase in understanding sustainable management.
Article
Full-text available
Farming faces challenges that increase the adverse effects on farms’ economics, labor, and the environment. Smart farming technologies (SFTs) are expected to assist in reverting this situation. In this work, 1064 SFTs were derived from scientific papers, research projects, and industrial products. They were classified by technology readiness level (TRL), typology, and field operation, and they were assessed for their economic, environmental, and labor impact, as well as their adoption readiness from end-users. It was shown that scientific articles dealt with SFTs of lower TRL than research projects. In scientific articles, researchers investigated mostly recording technologies, while, in research projects, they focused primarily on farm management information systems and robotic/automation systems. Scouting technologies were the main SFT type in scientific papers and research projects, but variable rate application technologies were mostly located in commercial products. In scientific papers, there was limited analysis of economic, environmental, and labor impact of the SFTs under investigation, while, in research projects, these impacts were studied thoroughly. Further, in commercial SFTs, the focus was on economic impact and less on labor and environmental issues. With respect to adoption readiness, it was found that all of the factors to facilitate SFT adoption became more positive moving from SFTs in scientific papers to fully functional commercial SFTs, indicating that SFTs reach the market when most of these factors are addressed for the benefit of the farmers. This SFT analysis is expected to inform researchers on adapting their research, as well as help policy-makers adjust their strategy toward digitized agriculture adoption and farmers with the current situation and future trends of SFTs.
Article
Full-text available
Introduction. It is believed that only 0.5 % of the area planted worldwide with cocoa is irrigated. Water availability influences the rate of expansion of the tree canopy and thus light interception. Another extremely important factor is pruning, which influences the production of floral sprouts that will give rise to new fruits, influencing productivity. Objective. The objective of this study was to evaluate the effect of drip irrigation and pruning on the performance, phenology and phytosanitary behavior of cacao trees. Materials and methods. The study was developed between 2015 and 2016 in the Cauca department, Colombia. The six-year-old trees were subjected to two watering layers: L-100 % and L-0 % and two pruning levels: soft and strong. Total number of fruits, number of healthy and sick fruits, kg of wet and dry cocoa, fruit index and seed index, longitudinal and equatorial diameters and incidence of Moniliopthora roreri, Phytophthora palmivora and Monalonion dissimulatum were evaluated. The growth and development curves of the fruit throughout time were built. An experimental design of complete random blocks was used in an arrangement of divide plots. Results. Fruit index varied from 22 (T2) up to 33 fruits (T3), the seed index varied from 0.91 g (T4) to 1.14 g (T2). There were no other significant results for other variables. Conclusion. From a technical and economic point of view an optimal response to the interaction of irrigation with the two levels of pruning was observed because, with a timely application of watering and an adequate pruning management, crop performance can be increased, harvests can be programmed and better quality fruits can be obtained.
Article
Full-text available
This article analyses welfare impacts of fertiliser adoption using data collected from 838 cocoa farm households in the four key cocoa-producing regions in Ghana. Using propensity score matching (PSM), the study indicates that application of fertiliser leads to significant gains in farm yields, farm income, consumption expenditure, consumption expenditure per capita, and value of productive farm assets. The article concludes that cocoa-specific programmes such as Cocoa High Technology (Cocoa Hi-tech), initiated to intensify the application of improved farm technologies such as fertiliser, should be strengthened through effective and efficient management systems.
Article
Full-text available
The deployment of plantain shade and irrigation (5- and 10-day) intervals) for enhancing survival, field establishment, flowering and pod production of field-grown cacao seedlings in the dry season was investigated. The effects of dry season irrigation was profound on cacao growth, field establishment (over 90% seedling survival) and development, flowering and pod production. For the non-irrigated moderately shaded cacao, about 30% of the transplanted seedlings survived and the achievable percent survival from the various shade-irrigation combinations ranged from 47–90%. Open sun in combination with 5-day irrigation interval had best results in term of growth (root and shoot development and biomass accumulation) and establishment, flowering and pod production. Lower values of air and soil temperatures were obtained for combination of irrigation and shade regimes (dense and moderate) and higher soil moisture contents. The shade-irrigation combinations ameliorated microclimate and enhanced growth and development, seedling survival, root and shoot development, advanced flowering and promoted uniform fruiting/pod production and total bean yield. The effects of dry season irrigation at 5- or 10-day intervals was profound on cacao growth, field establishment (over 90% seedling survival), flowering and pod production. Irrigated unshaded (open sun) cacao had best results in term of growth (root and shoot development and biomass accumulation) and establishment, flowering and pod production. The achievable percent survival from the various shade-irrigation combinations ranged from 47–90%. The drip irrigation strategy adopted ameliorated dry season terminal drought (hydrothermal stresses) and promoted cacao growth, survival and flower/pod production.
Article
Full-text available
The Benders decomposition algorithm has been successfully applied to a wide range of difficult optimization problems. This paper presents a state-of-the-art survey of this algorithm, with an emphasis on its use in combinatorial optimization. We discuss the classical algorithm, the impact of the problem formulation on its convergence, and the relationship to other decomposition methods. We introduce a taxonomy of algorithmic enhancements and acceleration strategies based on the main components of the algorithm. The taxonomy provides the framework to synthesize the literature, and to identify shortcomings, trends and potential research directions. We also discuss the use of the Benders decomposition to develop efficient (meta-)heuristics, describe the limitations of the classical algorithm, and present extensions enabling its application to a broader range of problems.
Article
Full-text available
Resistance of fourteen Theobroma cacao clones to Phytophthora spp. was evaluated using stem inoculations on grafted seedlings. Concepts of phenotypic stability were used to interpret the results and to express horizontality of the resistance. The linear regression coefficient 'b', the determination coefficient (R2) and average lesion size were used to determine the level of horizontal resistance, the phenotypic stability and the predictability of all clones. The results indicated that clones P 7 and MA 15 present highest levels of horizontal resistance and stability, but with moderate predictability. Clones CAS 1 and CEPEC 13 were classified as those with high horizontal resistance, stability and predictability, while clones PA 30, UF 650 and SIAL 88 and EET 59 showed intermediate resistance and stability and high predictability. Clones SPA 17, OC 61, PA 150, SIAL 505, ICS 1 and R 41 presented high susceptibility and intermediate or low stability and moderate or high predictability.
Book
This rapidly developing field encompasses many disciplines including operations research, mathematics, and probability. Conversely, it is being applied in a wide variety of subjects ranging from agriculture to financial planning and from industrial engineering to computer networks. This textbook provides a first course in stochastic programming suitable for students with a basic knowledge of linear programming, elementary analysis, and probability. The authors present a broad overview of the main themes and methods of the subject, thus helping students develop an intuition for how to model uncertainty into mathematical problems, what uncertainty changes bring to the decision process, and what techniques help to manage uncertainty in solving the problems. The early chapters introduce some worked examples of stochastic programming, demonstrate how a stochastic model is formally built, develop the properties of stochastic programs and the basic solution techniques used to solve them. The book then goes on to cover approximation and sampling techniques and is rounded off by an in-depth case study. A well-paced and wide-ranging introduction to this subject.
Chapter
Over the past several decades, linear programming (LP) has established itself as one of the most fundamental tools for planning. Its applications have become routine in several disciplines including those within engineering, business, economics, environmental studies and many others. One may attribute this wide spread acceptance to: (a) an understanding of the power and scope of LP among practitioners, (b) good algorithms, and (c) widely available and reliable software. Furthermore, research on specialized problems (e.g. assignment, transportation, networks etc.) has made LP methodology indispensible to numerous industries including transportation, energy, manufacturing and telecommunications, to name a few. Notwithstanding its success, we note that traditional LP models are deterministic models. That is, all objective function and constraint coefficients are assumed to be known with precision. The assumption that all model parameters are known with certainty serves to limit the usefulness of the approach when planning under uncertainty.