Portafolio

El documento analiza la transformación digital en el sector agropecuario mexicano, enfatizando su relevancia para mejorar la sostenibilidad, la resiliencia climática y la eficiencia institucional en zonas rurales. Dividido en dos apartados, el primero aborda conceptos clave de digitalización, brechas digitales, estrategias regionales y herramientas digitales disponibles, mientras que el segundo explora tecnologías específicas como inteligencia artificial, Internet de las cosas, blockchain, cómputo en la nube y desarrollo de software aplicado a la agricultura. Asimismo, se presentan recomendaciones para la implementación de soluciones digitales que faciliten el acceso a la información, promuevan la inclusión social y fortalezcan la integración de los sistemas de información en la producción y comercialización agropecuaria.

Reinforcement learning is a promising artificial maximizes a particular reward by mapping states to actions in a non-deterministic environment, intelligence area which relies on computational simulations where an agent finds a policy that applications in optimization problems. Here, we apply Q-learning, a popular model-free with learning algorithm to a representative ecological problem: the sustainable harvest of a reinforcement which follows a logistic growth rate by modeling it as a valid python gymnasium environment, population contributing to the generation of new environments which represent real-world situations and may lead to decision making. We implemented three different scenarios in which the agents determined an optimal policy guided by different reward signals: a greedy agent, which harvests as much as possible; a conscious agent, which seeks to harvest as much as possible while maintaining high population numbers; and a biocentric agent, which harvests only what is needed to avoid the population to exceed the carrying capacity of the environment. By initializing the population size to 100, with a growth rate of 1 and a carrying capacity of 200, the biocentric agent had the largest accumulated harvest, suggesting that a sustainable strategy is more profitable in the long term. Reinforcement learning is a very promising approach for decision making in many ecological real-world situations, where population management is a very straightforward application.

Envisioning trajectories towards sustainability encompasses enacting significant changes in multiple spheres (i.e., infrastructure, policy, practices, behaviors). These changes unfold within the intricate landscapes of wicked problems, where diverse perspectives and potential solutions intersect and often clash. Advancing more equitable and sustainable trajectories demands recognition of and collaboration with diverse voices to uncover meaningful synergies among groups striving to catalyze substantial change. Projects of this nature necessitate the exploration of varied tools and methodologies to elicit, convey, and integrate ideas effectively. Creating spaces for reflexivity is essential for catalyzing more meaningful impact as individuals engage in discussions aimed at sharing and questioning the coherence of their projects while forging synergies, identifying common objectives, and planning long-term outcomes. We present the initial phase of an endeavor in which we developed a software that elicits causal networks based on mapping relations between projects’ actions and outcomes. To illustrate our approach, we describe the results of using this software within collaborative workshops with groups spearheading projects initiated by a government entity in Mexico City. By adapting elements of the Theory of Change model, this software transcends the dominant linear project logic by guiding participants in designing causation networks that unveil how different projects can articulate to identify potential common elements and find new possibilities for coordination among initiatives. We discuss the potential of such software application as a dynamic tool to guide and promote reflection and coherence when crafting projects that aim to more meaningfully address sustainability problems.

El presente documento (y sus archivos anexados) es un esfuerzo para generar una base de datos para la Dirección Regional Centro y Eje Neovolcánico (DRCEN) de la Comisión Nacional de Áreas Naturales Protegidas (CONANP) en México. El resultado, es una propuesta de una base de datos relacional2 mantenible en el tiempo que sirva para sustentar una toma de decisiones efectiva basada en datos y evidencia, así como para la generación de insumos como podrían ser reportes, tableros (dashboards), gráficos, etc. Realizado por Salvador Garcilita (fundador de bioalgoritmia) cuando fungía como asesor en la cooperación alemana para el desarrollo (GIZ).