Predicting Ground-based Aerosol Optical Depth with Satellite Images Via Gaussian Processes

نویسندگان

  • Goo Jun
  • Joydeep Ghosh
  • Vladan Radosavljevic
  • Zoran Obradovic
چکیده

A Gaussian process regression technique is proposed to predict ground-based aerosol optical depth measurements from satellite multispectral images, and to select the most informative ground-based sites by active learning. Satellite images provide spatial and temporal information in addition to the spectral features, and such heterogeneity of available features is captured in the Gaussian process model by employing an additive set of covariance functions. By finding an optimal set of hyperparameters, relevance of each additional information is automatically determined. Experiments show that the spatio-temporal information contributes significantly to the regression results. The prediction results are not only more accurate but also more interpretable than existing approaches. For active learning, each spatio-temporal setup is evaluated by an uncertainty-sampling algorithm. The results show that the active selection process benefits most from the spatial information.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Aerosol Optical Depth Spatial and Temporal Variability Using Satellite Data Over Indian Major Cities

Introduction: The study’s main aim is to investigate the long-term variation of Aerosol Optical Depth (AOD). It also aims to show the relationship between meteorological parameters. This study evaluates long-term (2010 to 2021) special and temporal changes over major Indian regions using satellite-based data from NASA’s Terra Satellite. Materials and Methods: This study was carried out during ...

متن کامل

Investigating the relationship between ground-level particulate matter and aerosol optical depth during dust storm episodes: a case study of Tehran

Background and Objective: During the last few years, air pollution and increasing levels of particulate matters (PMs) have become major public health issues in the megacity of Tehran. The high cost of constructing and maintaining air pollution monitoring stations has made it difficult to achieve adequate spatial-temporal coverage of PM data over various regions. In this regard, the use of remot...

متن کامل

بهره گیری از سری زمانی داده های ماهواره ای به منظور اعتبارسنجی کانون های شناسایی شده تولید گرد و غبار استان البرز

Dust is one of the common processes of arid and semiarid regions that its occurrence frequencies has increased in recent years in Iran. The proper identification of sand and dust storms (SDS) is particular importance due to its impact on the environment and human health. So far, several methods for identifying these sources have been proposed such as methods based on field studies and geomorpho...

متن کامل

ارائه روشی سریع برای حذف اثر هوآویزها از تصاویر ماهواره‌ای MODIS

Due to the effect of aerosols present in the atmosphere on the satellite images, the study of the effect of local aerosols distribution on the satellite images is important. On the other hand, the study shows that the effect of aerosols on the greenhouse gases and consequently on climate is also undeniable and as a result, this puts more emphasize on the necessity of this study. Lack of informa...

متن کامل

Estimating surface visibility at Hong Kong from ground-based LIDAR, sun photometer and operational MODIS products.

Hong Kong's surface visibility has decreased in recent years due to air pollution from rapid social and economic development in the region. In addition to deteriorating health standards, reduced visibility disrupts routine civil and public operations, most notably transportation and aviation. Regional estimates of visibility solved operationally using available ground and satellite-based estima...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2010