We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Detection of Vegetation Spectral Signatures in Hyperspectral Images using Artificial Neural Networks
Summary
This study developed a computer program that can identify plants and vegetation in detailed satellite images by analyzing how they reflect different colors of light. The technology successfully detected about 42% of an area as vegetation in a test neighborhood, which was more accurate than older methods. This could help scientists better monitor environmental changes like deforestation or urban green spaces that affect air quality and human health.
Considering the challenge in hyperspectral imaging of developing new computational methods that strike a balance between accurate material classification and computational complexity, this work proposes the design and tunability of a model based on a sequential artificial neural network (ANN) to classify vegetation in hyperspectral images with 380 bands. To carry out this research, an adaptation of the CRISP-DM methodology was used, structured into four phases: P1. Business and data understanding, P2. Data preparation, P3. Modeling and evaluation, and P4. Modl application. As a result, a sequential ANN model was developed, featuring 380 input layers and a single output layer, along with a set of dense layers containing 12, 8 and 4 artificial neurons. After 20 epochs, the model showed high performance and consistent behavior in the training and test sets under the experimental setup considered. The model was applied to a hyperspectral image of the Manga neighborhood in Cartagena, classifying 41.921% of the image pixels as vegetation. This percentage of points exceeds by 12.941% the percentage obtained by the spectral differential similarity method, in which less continuous point detections were observed. This method is a viable alternative for use in environmental monitoring systems, especially when applied in parallel to large-scale images.
Sign in to start a discussion.
More Papers Like This
Neural network-aided classification of hyperspectral vegetation images with a training sample generated using an adaptive vegetation index
This paper presents a machine learning approach using neural networks to classify plant types in high-resolution hyperspectral aerial images of agricultural fields. The method could be applied to environmental monitoring, including detecting plastic contamination or pollution-induced vegetation changes in farmland.
A new band selection framework for hyperspectral remote sensing image classification
Researchers developed a new framework for reducing data complexity in hyperspectral satellite images by combining dual band selection with a convolutional neural network, achieving over 97% classification accuracy across three benchmark datasets. This approach could improve remote sensing applications like land cover mapping and environmental monitoring.
Flux to Flow: a Clearer View of Earth’s Water Cycle Via Neural Networks and Satellite Data
This dissertation developed neural network methods to enhance the spatial resolution of satellite measurements of Earth's water cycle, enabling finer-scale monitoring of hydrological processes such as precipitation, evaporation, and runoff across diverse environments.
Deep Intrinsic Decomposition with Adversarial Learning for Hyperspectral Image Classification
This paper presents a deep learning method for hyperspectral image classification that accounts for complex environmental variation causing within-class spectral differences. Such techniques may have applications in automated detection and identification of microplastics in environmental samples using spectral imaging.
Identification for the species of aquatic higher plants in the Taihu Lake basin based on hyperspectral remote sensing
Researchers developed a hyperspectral remote sensing method using a C4.5 decision tree algorithm to identify and map eight aquatic higher plant species in the Taihu Lake basin, addressing the challenge of distinguishing species with small spectral differences against dynamic water optical backgrounds. The approach enables large-scale, fine-resolution monitoring of aquatic plant distribution as an indicator of ecosystem health.