Elaheٍ Akbari; M Hajeb; Mehrdad Jeihouni; Saeid Hamzeh
Abstract
To determine the effect of the leaf biochemical contents on its spectral reflectance behavior via remote sensing (RS) can help to understand the process of the ecosystem and its parameters such as plant water stress. The present study aimed to do a quantitative analysis of the effect of leaf parameters, ...
Read More
To determine the effect of the leaf biochemical contents on its spectral reflectance behavior via remote sensing (RS) can help to understand the process of the ecosystem and its parameters such as plant water stress. The present study aimed to do a quantitative analysis of the effect of leaf parameters, including the amount of leaf chlorophyll, leaf structure, and leaf water content, on the leaf spectral reflectance. To this end, the PROSPECT radiative transfer model which developed to simulate the spectral behavior of plant leaves, was employed. The research results showed that the increase of chlorophyll with the effect of reducing the leaf spectral reflectance leads to the increase of Triangular Vegetation Indices (TVIs). In the visible light spectrum, it is possible to distinguish monocotyledons (monocots), dicotyledons (dicots), and old plants. Also, in the near-infrared (NIR) light spectrum, the amount of reflection decreases in old and unstructured plants, dicotyledonous plants, and monocotyledonous plants, respectively. The drying of the plant does not have much effect on the reflection, but drying more than a certain amount causes a significant increase in the reflection, especially outside the water absorption spectra. Therefore, finding the critical points of the reflectance curve against the water content can contribute to detecting severe water stress in plants. By examining the graphs, it can be observed that the critical point occurs about the water content of 0.03 to 0.04 g⁄〖cm〗^2 . In the PROSPECT radiative model, the effect of soil on the spectral reflectance of plants is not considered. Therefore, it is recommended to use models such as SAIL and SLC that have been upgraded for this purpose.
Mohammad Hajeb; Saeid Hamzeh; Seyed Kazem Alavipanah; Jochem Verrelst
Abstract
Leaf Area Index (LAI) plays a critical role in the mass and energy exchanges between the earth and the atmosphere. Like of other plants, LAI of sugarcane is a good indicator of the health status and growth of this crop which is of great economic importance due to its role in the food and energy industries. ...
Read More
Leaf Area Index (LAI) plays a critical role in the mass and energy exchanges between the earth and the atmosphere. Like of other plants, LAI of sugarcane is a good indicator of the health status and growth of this crop which is of great economic importance due to its role in the food and energy industries. Launched in 2019, the PRISMA satellite provides one of the most recent hyperspectral data sources which are applicable especially for mapping plant variables. In this study, a new kind of Artificial Neural Networks (ANN) so-called Bayesian Regularized Artificial Neural Networkk (BRANN) which applies Bayes' theorem to overcome the overfitting problem of neural networks is used. The model was implemented on a data set consisting of spectrum obtained by PRISMA satellite as an independent variable and sugarcane LAI measurements as a dependent variable. The ground measurements of sugarcane LAI were carried out in 118 elementary sampling units on the fields of Amir Kabir sugarcane cultivation and industry in Khuzestan province and on seven different dates during a sugarcane growth period in 2020. Comparing the performance of BRANN in retrieving sugarcane LAI from PRISMA spectra with that of a conventional ANN trained with the Levenberg-Marquardt algorithm (LMANN) indicates that the retrieval RMSE is reduced from 2.26 m2/m2 applying LMANN to 0.67 m2/m2 applying the BRANN method. In this study, the principle component analysis was also used dimensionality reduction. Retrieving LAI from the first 20 principle components, RMSE was also reduced from 1.41 m2/m2 applying LMANN to 0.71 m2/m2 applying BRANN. Exploiting principal components significantly reduced computational time. By implementing the calibrated BRANN model over the PRISMA image pixel by pixel, the sugarcane LAI map was generated. Evaluating this map showed that this map represents the spatial variations of sugarcane LAI well. The results of this study indicate the high performance of the BRANN method and high potential of PRISMA images to retrieve sugarcane LAI.
A.A Matkan; M Hajeb; M Eslami
Volume 7, Issue 2 , November 2015, , Pages 19-34
Abstract
The availability ofinformation about roads has great importanceinvariousapplicationssuch as transportation,traffic controlsystems, automatic navigation system, etc. In recent years, designing new road extraction algorithms has become the target of many studies by researchers. Despite the achieved progress, ...
Read More
The availability ofinformation about roads has great importanceinvariousapplicationssuch as transportation,traffic controlsystems, automatic navigation system, etc. In recent years, designing new road extraction algorithms has become the target of many studies by researchers. Despite the achieved progress, there are some defects in this field. The gaps in detected roads are one the most important of them. The gaps are appeared due to getting placed under trees, shadow or any other reason. Since the continuity of roads is a momentous topological trait, so filling the gaps seems necessary. The main aim of this paper is to provide a method to automatic find and fill the existing gaps in the extracted road net. Our algorithm first applies the Radon transformation to find the source and destination endpoints of the gaps, then connect these points together using Spline interpolation. This algorithm is implemented on a real detected road which has 4 gaps in straight roads and 2 gaps in junctions. The experiment shows that the proposed algorithm can correctly fill all of the gaps in straight roads, but it is not able to fill the gaps in junctions. So, regardless of the location of the gap, straight road or junction, it can be said that about 66.7% of the existing gaps was filled by the algorithm. This gap filling algorithm is implemented in MATLAB software