Uno de los principales problemas que enfrentan los métodos de enseñanza de las ciencias básicas y las ingenierías, es la separación del conocimiento teórico de la formación práctica. En este sentido, las experiencias en laboratorio se convierten en estrategias didácticas pedagógicas muy provechosas; sin embargo, implementarlas requiere de infraestructura física, equipos y materiales que originan grandes inversiones económicas. Como respuesta a esta problemática surge FisicaTIC, una plataforma hardware-software, que permite realizar diversas prácticas de física e ingeniería relacionadas con la cinemática y dinámica de los cuerpos. Esta propuesta pretende desarrollar habilidades de aprendizaje, con la ayuda de las propias herramientas tecnológicas del estudiante, (Smartphone, PC o Tablet). Para el desarrollo de software, se empleó como base metodológica “SCRUM”, sin embargo, esta metodología se integró a un modelo en V, teniendo en cuenta que esta técnica de desarrollo es eficiente para la materialización de productos tecnológicos que requieren de la implementación de subsistemas embebidos de hardware y software, ya que permite precisar con mayor nivel de detalle las herramientas a utilizar en cada una de las fases de desarrollo del producto. Para la validación y verificación del software y hardware construido. Se empleó como referente el estándar IEEE 1012-2016. Finalmente, se debe mencionar que los resultados obtenidos mediante el uso de FisicaTIC, permiten inferir que los estudiantes desarrollan habilidades cognoscitivas durante su interacción con el sistema construido, favoreciendo el abordaje y la comprensión de conceptos relacionados con la cinemática, las fuerzas gravitatorias y el movimiento armónico simple.

The early detection of Brown Spot disease (Bipolaris oryzae) in tropical rice crops is hindered by the phenotypic ambiguity of early-stage lesions and the complexity of background noise in open-field canopies. Traditional monitoring methods often fail due to the spectral saturation of structural indices in dense vegetation. This study proposes a novel framework integrating proximal multispectral sensing (h = 40–50 cm) with a modernized deep learning architecture. Through a high-throughput audit of 17 multispectral indices, we engineered a high-dimensional Bio-Spectral Tensor fusing the Chlorophyll Vegetation Index (CVI), Modified Anthocyanin Content Index (MACI), and Green Normalized Difference Vegetation Index (GNDVI).Statistical analysis via the Fisher Discriminant Criterion revealed that CVI provides a 144-fold increase in class-discriminative power compared to the industry-standard NDVI, effectively decoupling biotic stress signals from environmental artifacts. These tensors were processed using the ConvNeXt architecture, a modernized convolutional model optimized for high-dimensional feature extraction. The system achieved an overall classification accuracy of 98.0% and a Recall of 1.00 for the diseased class, ensuring zero false negatives in phytosanitary monitoring. Furthermore, Explainable AI (Grad-CAM) analysis validated that the network's decision-making is driven by physiological lesion signatures—specifically necrotic centers and chlorotic halos—rather than background noise. These findings establish a scalable, physics-informed baseline for autonomous crop health monitoring in the Colombian tropics.

Research project formulation remains one of the least formalized tasks in scientific practice. Proposals are developed iteratively, with each component retroactively conditioning the others, while the decision of when a proposal is sufficiently complete still lacks a computable criterion. Current artificial intelligence tools support text generation, synthesis, and information retrieval, but, to our knowledge, none explicitly models formulation as a convergence problem subject to methodological constraints or defines a formal stopping rule. This paper introduces FARO (Augmented Formulation and Optimized Review via Artificial Intelligence), a framework that represents a research proposal as a directed methodological graph, quantifies its global coherence through a weighted loss function, refines it through conceptual backpropagation, and verifies it using structural consistency checks. Baseline uncertainty is quantified through a four-dimensional index U₀ (α = 0.941, n = 26), which sets module activation and the adaptive rigor parameter SE_τ. For accepted updates, we establish that the loss decreases monotonically; deterministic code-level constraints enforce this property independently of the generative model. A Variance Inflation Factor analogue formalizes semantic redundancy among diagnostic queries, orthogonal to inter-node contradiction. An ordinal decision layer with an abstention option expresses irreducible terminal uncertainty as a probability of favorable evaluation, to be calibrated empirically, and routes unresolved items to an actionable risk map. Operational evidence comes from 155 iterations of a real pilot project; multi-project validation and empirical calibration are underway.

Field-based phenotyping of water-related traits for precision irrigation in tropical agroecosystems poses a persistent methodological challenge, driven by high climatic variability and the complex water-use physiology of Crassulacean Acid Metabolism (CAM) crops such as pineapple (Ananas comosus var. MD2). We developed and validated a Physics-Informed Machine Learning (PIML) framework that integrates high-resolution UAV multispectral imagery, IoT-based microclimatic records, and a mechanistic soil water balance based on the FAO-56 Penman–Monteith standard to predict plot-scale soil moisture depletion as a proxy of plant water status. A six-month field campaign (March–August 2022) across 25 georeferenced commercial pineapple plots in the Colombian Orinoquia piedmont yielded a spatiotemporally balanced dataset of $N=150$ observations. Soil-adjusted vegetation indices (OSAVI, MSAVI) outperformed standard NDVI for capturing water-related canopy traits, effectively decoupling spectral responses from substrate noise. A Gradient Boosting regressor achieved $R^2=0.842$ and $RMSE=0.0705$ on a normalized target scale, corresponding to a $7.05\%$ error over the prediction range, while the traffic-light Decision Support System (DSS) for irrigation scheduling reached $91.1\%$ accuracy (Cohen’s Kappa $=0.91$). Incorporating daily soil moisture depletion as a mechanistic feature improved predictive accuracy over a spectral-only baseline ($\mathrm{\Delta }{R}^2=+0.052$) and anchored predictions within a physically consistent framework based on the FAO-56 water balance, with no false negatives observed for water deficit detection in the hold-out validation set. This framework advances high-throughput, population-scale phenotyping of water-related traits in open-canopy CAM crops, establishing a transferable methodology for operational precision irrigation under tropical savanna conditions.