Abdullah F. Rahman

Comparing the performance of multispectral vegetation indices and machine-learning algorithms for remote estimation of chlorophyll content: a case study in the Sundarbans mangrove forest

Optical vegetation indices (VIs) have been used to retrieve and assess biophysical variables from satellite reflectance data. These indices, however, also are sensitive to a number of confounding factors, such as canopy geometry, soil optical properties, and solar position. This suggests that VIs should be used cautiously for biophysical parameter estimation. Among biophysical variables, chlorophyll content is of particular importance as an indicator of photosynthetic activity. The goal of this study is to investigate the performance of multispectral optical VIs for chlorophyll content estimation in the world’s largest mangrove forest, the Sundarbans, and to compare these with machine-learning algorithms (MLAs). To this end, we have investigated the performance of 15 multispectral VIs and six state-of-the-art MLAs that are widely used for adaptive data fitting. The MLAs are Artificial Neural Networks (ANNs), Genetic Algorithm (GA), Gaussian Processes for Machine Learning (GPML), Kernel Ridge Regression (KRR), Locally Weighted Polynomials (LWP), and Multivariate Adaptive Regression Splines (MARS). We use an in situ data set of reflectance and chlorophyll measurements to develop and validate our models. Each MLA was evaluated 500 times with random partitions of training and validation data. Results showed that the weight optimization and term selection used within GA produce the most reliable chlorophyll content estimation. However, green normalized difference VI (GNDVI) is a simple and computationally efficient VI that produces results that are nearly as accurate as GA in terms of model fit and performance. Results also show that all methods except ANNs and MARS produce a quasi-linear relationship between spectral reflectance and chlorophyll content. Statistical transformations of GNDVI and chlorophyll content have the capability of further reducing model error.

Automatic Seagrass Disturbance Pattern Identification on Sonar Images

Natural and anthropogenic disturbances are causing degradation and loss of seagrass cover, often in the form of bare patches (potholes) and propeller-scaring from vessels. Degradation of seagrass habitat has increased significantly in recent years with losses totaling some 110 km2 per year. With seagrass habitat disappearing at historically unprecedented rates, development of new tools for mapping these disturbances is critical to understanding habitat distribution and seagrass abundance. Current methods for mapping seagrass coverage rely on appropriate meteorological conditions (satellite imagery), are high in cost (aerial photography), or lack resolution (in situ point surveys). All of these methods require low turbidity, and none is capable of automatically detecting bare patches (potholes) in seagrass habitat. Sonar-based methods for mapping seagrass can function in high turbidity, and are not affected by meteorological conditions. Here, we present an automatic method for detecting and quantifying potholes in sidescan sonar images collected in a very shallow, highly disturbed seagrass bed. Acoustic studies of shallow seagrass beds (<2 m) are scarce due to traditional approaches being limited by reduced horizontal swath in these depth ranges. The main challenges associated with these sidescan sonar images are random ambient noise and uneven backscatter intensity across the image. Our method combines adaptive histogram equalization and top-hat mathematical morphology transformation to remove image noises and irregularities. Then, boundaries of potholes are detected using optimum binarization as well as closing and erosion mathematical morphology filters. This method was applied to several sonar images taken from the Lower Laguna Madre in Texas at less than 2-m depth. Experimental results in comparison with ground-truthing demonstrated the effectiveness method by identifying potholes with 97% accuracy.

Effect of carbon content on sound speed and attenuation of sediments in seagrass meadows

Globally, seagrass-bearing sediments contain 19.9 billion metric tons of carbon (C), and account for 10% of all organic C buried in the ocean each year. Protection of these C stores is vital in mitigating climate change [Fourqurean, J. W., et al., Nature Geoscience 5, 505–509 (2012)]. Some sediment acoustic properties are sensitive to the presence of gas bubbles entrained in such C stores due to inherent anaerobic decomposition. Measurement of these properties could therefore provide a means to indirectly monitor C stores and overall seagrass meadow productivity. As a preliminary effort to investigate the relationship between C content and acoustic properties of seagrass-bearing sediments, cores were collected in the seagrass meadows of Lower Laguna Madre, Texas. Sound speed and attenuation from 100 kHz to 300 kHz were measured radially in 2-cm-depth increments. The cores were subsequently frozen, sliced along the same depth increments, and their C content estimated using an elemental analyzer. Acoustic p...

The First Automatic Method for Mapping the Pothole in Seagrass

There is a vital need to map seagrass ecosystems in order to determine worldwide abundance and distribution. Currently there is no established method for mapping the pothole or scars in seagrass. Detection of seagrass with optical remote sensing is challenged by the fact that light is attenuated as it passes through the water column and reflects back from the benthos. Optical remote sensing of seagrass is only possible if the water is shallow and relatively clear. In reality, coastal waters are commonly turbid, and seagrasses can grow under 10 meters of water or even deeper. One of the most precise sensors to map the seagrass disturbance is side scan sonar. Underwater acoustics mapping produces a high definition, two-dimensional sonar image of seagrass ecosystems. This paper proposes a methodology which detects seagrass potholes in sonar images. Side scan sonar images usually contain speckle noise and uneven illumination across the image. Moreover, disturbance presents complex patterns where most segmentation techniques will fail. In this paper, the quality of image is improved in the first stage using adaptive thresholding and wavelet denoising techniques. In the next step, a novel level set technique is applied to identify the pothole patterns. Our method is robust to noise and uneven illumination. Moreover it can detect the complex pothole patterns. We tested our proposed approach on a collection of underwater sonar images taken from Laguna Madre in Texas. Experimental results in comparison with the ground-truth show the efficiency of the proposed method.

Acoustical characterization of a seagrass meadow in the Lower Laguna Madre

This talk presents preliminary results from an experiment conducted in the Lower Laguna Madre, Texas to characterize the physical and acoustical properties in a meadow of Thalassia testudinum. Concurrent measurements were collected using (1) acoustic probes, (2) side-scan and parametric sonar, (3) broadband propagation, and (4) sediment cores. The acoustic probes provided localized, direct measurements of sound propagation in the seagrass canopy as well as geoacoustic properties (compressional and shear wave speed and attenuation) of the seagrass-bearing sediment. The side-scan and parametric sonars were used to survey for seagrass abundance and sub-bottom layering. Broadband signals produced by a combustive sound source were recorded at several ranges by hydrophones and geophones and were used to infer geoacoustic properties of the seagrass and underlying sediment for rapid environmental assessment. The sediment cores were analyzed in the laboratory using both low-frequency resonator measurements and hig...

Detecting red tide using spectral shapes

Red tide is a harmful algal bloom (HAB) caused by the dinoflagellate Karenia brevis, which occurs in the Gulf of Mexico (GOM) almost every year. We developed a red tide index (RTI) based on reflectance data from the new Landsat 8 satellite, which has two blue bands that can track the reflectance of carotenoid photopigments present in K. brevis. RTI has a range of 0-100, can be correlated with cell counts of K. brevis from field observations, and can be used to produce red tide maps at 30 m pixel resolution. This is a new method of detecting red tide that can be used in conjunction with the existing coarse spatial resolution MODIS-based daily products to monitor the movement of red tide along the coastlines. This can provide a powerful tool to the public health agencies and government for managing coastal resources and protecting human health.