Abstract
In previous attempts to identify aquatic vegetation from remotely-sensed images using classification trees (CT), the images used to apply CT models to different times or locations necessarily originated from the same satellite sensor as that from which the original images used in model development came, greatly limiting the application of CT. We have developed an effective normalization method to improve the robustness of CT models when applied to images originating from different sensors and dates. A total of 965 ground-truth samples of aquatic vegetation types were obtained in 2009 and 2010 in Taihu Lake, China. Using relevant spectral indices (SI) as classifiers, we manually developed a stable CT model structure and then applied a standard CT algorithm to obtain quantitative (optimal) thresholds from 2009 ground-truth data and images from Landsat7-ETM+, HJ-1B-CCD, Landsat5-TM and ALOS-AVNIR-2 sensors. Optimal CT thresholds produced average classification accuracies of 78.1%, 84.7% and 74.0% for emergent vegetation, floating-leaf vegetation and submerged vegetation, respectively. However, the optimal CT thresholds for different sensor images differed from each other, with an average relative variation (RV) of 6.40%. We developed and evaluated three new approaches to normalizing the images. The best-performing method (Method of 0.1% index scaling) normalized the SI images using tailored percentages of extreme pixel values. Using the images normalized by Method of 0.1% index scaling, CT models for a particular sensor in which thresholds were replaced by those from the models developed for images originating from other sensors provided average classification accuracies of 76.0%, 82.8% and 68.9% for emergent vegetation, floating-leaf vegetation and submerged vegetation, respectively. Applying the CT models developed for normalized 2009 images to 2010 images resulted in high classification (78.0%–93.3%) and overall (92.0%–93.1%) accuracies. Our results suggest that Method of 0.1% index scaling provides a feasible way to apply CT models directly to images from sensors or time periods that differ from those of the images used to develop the original models.
Highlights
Shallow freshwater lakes are some of the ecosystems most vulnerable to anthropogenic disturbance [1,2].With the development of socio-economic uses, global water pollution is becoming increasingly serious; more and more aquatic vegetative habitats are lost, which results directly in changes to aquatic vegetative productivity, distribution and biodiversity [3,4]
Because there is a high probability that a pixel with Normalized Difference Vegetation Index (NDVI) > 0.4 is vegetation, we identified the pixels in the algae type zone where NDVI > 0.4, using the ETM+ image of 20 August 2010, which was taken soon after a rainfall event caused a near absence of cyanobacterial blooms on the water surface
81.1% to 91.6% for other types, with respective averages of 78.1%, 84.7%, 74.0% and 86.2% (Figure 2). These results suggested that aquatic vegetation types in Taihu Lake could be distinguished using pre-developed classification trees (CT) model structures with optimal thresholds obtained from quantitative CT analysis of field observations
Summary
With the development of socio-economic uses, global water pollution is becoming increasingly serious; more and more aquatic vegetative habitats are lost, which results directly in changes to aquatic vegetative productivity, distribution and biodiversity [3,4]. Because of the important ecological and socio-economic functions of aquatic vegetation [5,6], dynamic monitoring at large spatial scales is important for lake management. To be effective and cost-efficient, such monitoring efforts require the development of aquatic vegetation maps using remotely sensed information [7,8,9,10,11]. Many successful classifications of aquatic vegetation have been achieved, with accuracies ranging from 67.1 to 96% [12,13,14,15,16,17,18], remote sensing techniques have not been used widely as a regular tool for monitoring aquatic vegetation changes, and more research is needed to help clarify the most appropriate and effective methods [1,12,19,20,21]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
