Video Experimental Relacionado
Updated: Feb 7, 2026

06:19
Constructing and Visualizing Models using Mime-based Machine-learning Framework
Published on: July 22, 2025
2.6K
Uso de GeoAI y Herramientas de Aprendizaje Automático para un Mapeo Consistente de Cobertura Terrestre de Alta
Research square
|February 6, 2026
Resumen
Este estudio desarrolló un algoritmo de GeoAI/Aprendizaje Automático para crear mapas consistentes de cobertura terrestre de 1 m a partir de datos del National Agricultural Imagery Program (NAIP). El método aborda las variaciones del sensor, lo que permite un monitoreo ecológico confiable a largo plazo.
Área de la Ciencia:
- Análisis geoespacial
- Aplicaciones de aprendizaje automático
- Teledetección
Sus antecedentes:
- Los mapas de cobertura terrestre a largo plazo y de alta resolución son cruciales para los estudios ecológicos, pero están limitados por la escasez de datos y las inconsistencias temporales.
- Los datos del National Agricultural Imagery Program (NAIP) ofrecen valiosas imágenes aéreas, pero sufren de heterogeneidad relacionada con el sensor, lo que dificulta la generación de mapas multianuales.
Objetivo del estudio:
- Desarrollar un algoritmo de GeoAI/Aprendizaje Automático para producir mapas de cobertura terrestre de 1 m espacialmente detallados y temporalmente coherentes utilizando imágenes de series temporales NAIP.
- Superar las variaciones de los sensores entre años en los datos NAIP sin requerir muestras de entrenamiento históricas.
Principales métodos:
- Se implementó un flujo de trabajo adaptativo de doble vía, aplicando estrategias distintas para imágenes NAIP de alta calidad (2009-2017) y de menor calidad (2004-2008).
- Las imágenes de alta calidad se clasificaron utilizando un modelo base U-Net/ResNet-34 refinado por un Modelo de Segmentación de Cualquier Cosa (SAM).
- Las imágenes de menor calidad se reconstruyeron utilizando un pipeline de vinculación espaciotemporal y retroceso de etiquetas basado en el National Land Cover Database (NLCD).
Principales resultados:
- El algoritmo logró resultados estables y consistentes a lo largo de los años, con precisiones generales de 0,874 (2014), 0,848 (2017) y 0,788 (2004).
- Se obtuvieron consistentemente puntuaciones F1 altas para las clases de Estructura, Agua, Humedal y Cultivos.
- El método mantuvo la fidelidad espacial y la consistencia temporal a pesar de las diferencias significativas de los sensores en las imágenes históricas.
Conclusiones:
- Las herramientas de GeoAI/Aprendizaje Automático y diversas fuentes de datos pueden generar de manera efectiva mapas de cobertura terrestre consistentes, de alta resolución y multidecadales a partir de imágenes NAIP.
- El enfoque desarrollado ofrece una solución escalable para crear mapas de cobertura terrestre de series temporales en todo el área contigua de EE. UU.
- Esto facilita el análisis de cambios de cobertura terrestre a largo plazo y la planificación a nivel de paisaje.
Palabras clave:
GeoAIAprendizaje automáticoMapeo de cobertura terrestreImágenes NAIPSeries temporalesMonitoreo ecológicoMás Videos Relacionados
Videos de Conceptos Relacionados
The Colonization of Land
37.7K
Changes in the environment of the early Earth drove the evolution of organisms. As prokaryotic organisms in the oceans began to photosynthesize, they produced oxygen. Eventually, oxygen saturated the oceans and entered the air, resulting in an increase in atmospheric oxygen concentration, known as the oxygen revolution approximately 2.3 billion years ago. Therefore, organisms that could use oxygen for cellular respiration had an advantage. More than 1.5 years ago, eukaryotic cells and...
37.7K
Time-Series Graph
5.2K
A time-series graph is a line graph with repeated measurements taken at successive intervals of time. It is also called a time series chart. To construct a time-series graph, one must look at both pieces of a paired data set. The horizontal axis is used to plot the time increments, and the vertical axis is used to plot the values of the variable that one is measuring. By using the axes in this way, each point on the graph will correspond to time and a measured quantity. The points on the graph...
5.2K
Discrete-Time Fourier Series
711
The Discrete-Time Fourier Series (DTFS) is a fundamental concept in signal processing, serving as the discrete-time counterpart to the continuous-time Fourier series. It allows for the representation and analysis of discrete-time periodic signals in terms of their frequency components. Unlike its continuous counterpart, which utilizes integrals, the calculation of DTFS expansion coefficients involves summations due to the discrete nature of the signal.
For a discrete-time periodic signal x[n]...
For a discrete-time periodic signal x[n]...
711
Machines
579
Machines are complex structures consisting of movable, pin-connected multi-force members that work together to transmit forces. One example of a machine is the cutting plier, which is used to cut wires by applying forces to its handles. When equal and opposite forces are exerted on the handles of the cutting plier, they cause the cutting edges to come together and apply equal and opposite reaction forces on the wire, which are greater than the applied forces.
A free-body diagram of the...
A free-body diagram of the...
579
Resistors In Series
6.6K
A resistor is an ohmic device that limits the flow of charge in a circuit. Most circuits have more than one resistor. If several resistors are connected together and connected to a battery, the current supplied by the battery depends on the equivalent resistance of the circuit. The equivalent resistance of a combination of resistors depends on both their individual values and how they are connected. The simplest combination of resistors is the series combination.
In a series circuit, the...
In a series circuit, the...
6.6K
Series Resonance
837
The RLC circuit impedance is defined as the ratio of the supply voltage to the circuit current. Resonance in such a circuit occurs when the imaginary part of this impedance equals zero. This specific condition means that the inductive reactance is exactly equal to the capacitive reactance. The frequency at which this happens is known as the resonant frequency. Mathematically, the resonant frequency is inversely proportional to the square root of the product of the inductance (L) and capacitance...
837

