Abstract
Time series land cover data statistics often fluctuate abruptly due to seasonal impact and other noise in the input image. Temporal smoothing techniques are used to reduce the noise in time series data used in land cover mapping. The effects of smoothing may vary based on the smoothing method and land cover category. In this study, we compared the performance of Fourier transformation smoothing, Whittaker smoother and Linear-Fit averaging smoother on Landsat 5, 7 and 8 based yearly composites to classify land cover in Province No. 1 of Nepal. The performance of each smoother was tested based on whether it was applied on image composites or on land cover primitives generated using the random forest machine learning method. The land cover data used in the study was from the years 2000 to 2018. Probability distribution was examined to check the quality of primitives and accuracy of the final land cover maps were accessed. The best results were found for the Whittaker smoothing for stable classes and Fourier smoothing for other classes. The results also show that classification using a properly selected smoothing algorithm outperforms a classification based on its unsmoothed data set. The final land cover generated by combining the best results obtained from different smoothing approaches increased our overall land cover map accuracy from 79.18% to 83.44%. This study shows that smoothing can result in a substantial increase in the quality of the results and that the smoothing approach should be carefully considered for each land cover class.
Highlights
Thematic land cover and forest maps are important sources of information for managers and policy makers for local and national-level policies and development strategies [1,2,3,4]
This study tested on using temporal smoothing as a means to improve land cover maps that were prepared by using a machine learning algorithm
We found that using temporal smoothing with machine learning improves the results compared to no smoothing; for classes that frequently undergo changes, Fourier smoothing produces the best results when applied on composite images
Summary
Thematic land cover and forest maps are important sources of information for managers and policy makers for local and national-level policies and development strategies [1,2,3,4]. Remote sensing is a widely-accepted method for land cover classification. Since commercial high resolution images, free medium resolution images and open source cloud computing platforms are becoming more available, using machine learning (ML) techniques to classify land cover types with remotely-sensed data has gained popularity [8,9]. Dealing with noise is one of the main challenges in satellite image classification schemes. Various techniques have been proposed to reduce the impact of noise. These methods include pre-processing of the input images or post-processing the results [12]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
