Modeling spatiotemporal patterns of land use/land cover change in Central Malawi using a neural network model

Leah Mungai Joseph Messina Leo Zulu Jiaguo Qi Sieglinde Snapp (2022, [Artículo])

Multilayer Perceptrons CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA AGRICULTURE LAND USE POPULATION SATELLITE IMAGERY TEXTURE LAND COVER NEURAL NETWORKS REMOTE SENSING

Difusión de cursos que la Fundación Carlos Slim ofrece en aprende.org

Cesar Petroli (2021, [Poster de congreso])

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA TRAINING AGRICULTURAL TRAINING SOCIAL NETWORKS TRAINING COURSES SUSTAINABLE AGRICULTURE

E. African spring wheat breeding pipeline and Network (CIMMYT-KALRO)

sridhar bhavani (2023, [Objeto de congreso])

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA WHEAT PLANT BREEDING RESEARCH NETWORKS

Chapter 9. Genome-informed discovery of genes and framework of functional genes in wheat

awais rasheed Rudi Appels (2024, [Capítulo de libro])

Wheat Genomics KASP Markers Gene Discovery Functional Markers Gene Networks CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA WHEAT GENOMICS SINGLE NUCLEOTIDE POLYMORPHISMS FUNCTIONAL GENOMICS

The contribution of strong and weak ties to resilience: The case of small-scale maize farming systems in Mexico

Tania Carolina Camacho Villa Ernesto Adair Zepeda Villarreal Julio Díaz-José Roberto Rendon-Medel Bram Govaerts (2023, [Artículo])

Social Network Analysis Farm Typologies Social Ties Strong Ties CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA INNOVATION NETWORKS PERSISTENCE SOCIAL NETWORK ANALYSIS MAIZE FARMING SYSTEMS

A Novel Technique for Classifying Bird Damage to Rapeseed Plants Based on a Deep Learning Algorithm.

Ali Mirzazadeh Afshin Azizi Yousef Abbaspour_Gilandeh José Luis Hernández-Hernández Mario Hernández Hernández Iván Gallardo Bernal (2021, [Artículo])

Estimation of crop damage plays a vital role in the management of fields in the agricultura sector. An accurate measure of it provides key guidance to support agricultural decision-making systems. The objective of the study was to propose a novel technique for classifying damaged crops based on a state-of-the-art deep learning algorithm. To this end, a dataset of rapeseed field images was gathered from the field after birds¿ attacks. The dataset consisted of three classes including undamaged, partially damaged, and fully damaged crops. Vgg16 and Res-Net50 as pre-trained deep convolutional neural networks were used to classify these classes. The overall classification accuracy reached 93.7% and 98.2% for the Vgg16 and the ResNet50 algorithms, respectively. The results indicated that a deep neural network has a high ability in distinguishing and categorizing different image-based datasets of rapeseed. The findings also revealed a great potential of Deep learning-based models to classify other damaged crops.

rapeseed classification damaged crops deep neural networks INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS TECNOLOGÍA DE LOS ALIMENTOS

Sorghum value chain analysis in semi-arid Zimbabwe

Abbyssinia Mushunje Munyaradzi Junia Mutenje Charles Pfukwa (2019, [Artículo])

Small Scale Farmers Extension Networks CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA AGRO-INDUSTRIAL SECTOR MARKETING MARGINS SORGHUM VALUE CHAINS

Appraisal of complementarity of subsurface drip fertigation and conservation agriculture for physiological performance and water economy of maize

C.M. Parihar Hari Sankar Nayak Dipaka Ranjan Sena Renu Pandey Mahesh Gathala ML JAT (2023, [Artículo])

The Indo-Gangetic Plains (IGP) in north-west (NW) India are facing a severe decline in ground water due to prevalent rice-based cropping systems. To combat this issue, conservation agriculture (CA) with an alternative crop/s, such as maize, is being promoted. Recently, surface drip fertigation has also been evaluated as a viable option to address low-nutrient use efficiency and water scarcity problems for cereals. While the individual benefits of CA and sub-surface drip (SSD) irrigation on water economy are well-established, information regarding their combined effect in cereal-based systems is lacking. Therefore, we conducted a two-year field experiment in maize, under an ongoing CA-based maize-wheat system, to evaluate the complementarity of CA with SSD irrigation through two technological interventions–– CA+ (residue retained CA + SSD), PCA+ (partial CA without residue + SSD) – at different N rates (0, 120 and 150 kg N ha-1) in comparison to traditional furrow irrigated (FI) CA and conventional tillage (CT) at 120 kg N ha-1. Our results showed that CA+ had the highest grain yield (8.2 t ha-1), followed by PCA+ (8.1 t ha-1). The grain yield under CA+ at 150 kg N ha-1 was 27% and 30% higher than CA and CT, respectively. Even at the same N level (120 kg N ha-1), CA+ outperformed CA and CT by 16% and 18%, respectively. The physiological performance of maize also revealed that CA+ based plots with 120 kg N ha-1 had 12% and 3% higher photosynthesis rate at knee-high and silking, respectively compared to FI-CA and CT. Overall, compared to the FI-CA and CT, SSD-based CA+ and PCA+ saved 54% irrigation water and increased water productivity (WP) by more than twice. Similarly, a greater number of split N application through fertigation in PCA+ and CA+ increased agronomic nitrogen use efficiency (NUE) and recover efficiency by 8–19% and 14–25%, respectively. Net returns from PCA+ and CA+ at 150 kg N ha-1 were significantly higher by US$ 491 and 456, respectively than the FI-CA and CT treatments. Therefore, CA coupled with SSD provided tangible benefits in terms of yield, irrigation water saving, WP, NUE and profitability. Efforts should be directed towards increasing farmers’ awareness of the benefits of such promising technology for the cultivating food grains and commercial crops such as maize. Concurrently, government support and strict policies are required to enhance the system adaptability.

Net Returns Subsurface Drip Irrigation Subsurface Drip Fertigation CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA EFFICIENCY GRAIN NITROGEN PHOTOSYNTHESIS PHYSIOLOGY WATER SUPPLY CONSERVATION AGRICULTURE CONVENTIONAL TILLAGE FERTIGATION GROUNDWATER NITROGEN-USE EFFICIENCY WATER PRODUCTIVITY

Digital artifacts reveal development and diffusion of climate research

Bia Carneiro Tek Sapkota (2022, [Artículo])

Accessible Knowledge Impact of Outputs Traditional Bibliometric Analyses Hyperlink Analysis CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA CLIMATE DIFFUSION MAIZE MINING ORGANIZATION SOCIAL MEDIA SOCIAL NETWORK ANALYSIS WHEAT TEXT MINING

Usando la descomposición de un grafo Halin para el diseño de algoritmos autoestabilizantes

Using Halin graph decomposition for the design of self-stabilizing algorithm

Daniel Uriel Orozco Lomelí (2023, [Tesis de maestría])

Sea G = (V, E) un grafo no dirigido. El problema de encontrar un conjunto independiente fuerte en G, es identificar un conjunto S ⊆ V , tal que dados dos vértices arbitrarios de S, éstos estén separados entre sí por el menos tres aristas. Encontrar un conjunto S de tamaño máximo pertenece a la clase NP-Difícil. Por otro lado, el problema de encontrar un conjunto dominante total en G es identificar un conjunto D ⊆ V , tal que cualquier vértice en V tenga al menos un vecino que pertenezca a D. Encontrar un conjunto D de tamaño mínimo también pertenece a la clase NP-Difícil. En este trabajo de tesis se diseñaron dos algoritmos, uno que resuelve el problema de encontrar un conjunto independiente fuerte maximal y otro que resuelve el problema de encontrar un conjunto dominante total minimal. Estos dos problemas son menos restrictivos que las versiones de optimización descritas al principio de este texto y se sabe que pertenecen a la clase P. Los algoritmos diseñados corren en un sistema distribuido, son autoestabilizantes, son tolerantes a fallas transitorias y funcionan para grafos Halin. Los grafos Halin pertenecen a la clase de grafos 2-outerplanares y tienen la propiedad de que se pueden partir en dos subgrafos muy conocidos, un árbol y un ciclo. Los algoritmos propuestos aprovechan la propiedad anterior para disminuir la complejidad de los mismos. Hasta donde tenemos conocimiento, los algoritmos propuestos, que corren en tiempo lineal en el número de vértices, son los algoritmos más rápidos existentes para los problemas del conjunto independiente fuerte maximal y el conjunto dominante total minimal.

Let G = (V, E) be an undirected graph. The problem of finding a strong stable set in G, is to identify a set S ⊆ V , such that given two arbitrary vertices of S, they are separated from each other by at least three edges. Finding a set S of maximum size belongs to the class NP-Hard. On the other hand, the problem of finding a total dominanting set in G is to identify a set D ⊆ V , such that any vertex in V has at least one neighbor belonging to D. Finding a set D of minimum size also belongs to the class NP-Hard. In this thesis work, two algorithms were designed, one that solves the problem of finding a maximal strong stable set and one that solves the problem of finding a minimal total dominanting set. These two problems are less restrictive than the optimization versions described at the beginning of this text and are known to belong to the P class. The designed algorithms run on a distributed system, are self-stabilizing, are transient fault tolerant, and work for Halin graphs. Halin graphs belong to the 2-outerplanar class of graphs and have the property that they can be split into two well-known subgraphs, a tree and a cycle. The proposed algorithms take advantage of the above property to decrease the complexity of the algorithms. To the best of our knowledge, the proposed algorithms, which run in linear time in the number of vertices, are the fastest existing algorithms for the maximal strong stable set and minimal total dominating set problems.

Grafo Halin, Sistemas Distribuidos, Autoestabilización, Conjunto Independiente Fuerte, Conjunto Dominante Total Halin Graph, Distributed Systems, Self-stabilizing, Strong Stable Set, Total Dominating Set INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS TECNOLOGÍA DE LOS ORDENADORES LENGUAJES ALGORÍTMICOS LENGUAJES ALGORÍTMICOS