Spatio-Temporal Resolution of Irradiance Samples in Machine Learning Approaches for Irradiance Forecasting

Epilepsy is a group of neurological disorders identifiable by infrequent but recurrent seizures. Seizure prediction is widely recognized as a significant problem in the neuroscience domain. Developing a Brain-Computer Interface (BCI) for seizure prediction can provide an alert to the patient, providing a buffer time to get the necessary emergency medication or at least be able to call for help, thus improving the quality of life of the patients. A considerable number of clinical studies presented evidence of symptoms (patterns) before seizure episodes and thus, there is large research on seizure prediction, however, there is very little existing literature that illustrates the use of structured processes in machine learning for predicting seizures. Limited training data and class imbalance (EEG segments corresponding to preictal phase, the duration just before the seizure, to about an hour prior to the episode, are usually in a tiny minority) are a few challenges that need to be addressed when employing machine learning for this task. In this paper we present a comparative study of various machine learning approaches that can be used for classification of EEG signals into preictal and interictal (Interictal is the time between seizures) using the features extracted from the intracranial EEG. Publicly available data has been used for this purpose for both human and canine subjects. After data pre-processing and extensive feature extraction, different models are trained and are effectively used to analyze the temporal dynamics of the brain (interictal and preictal) in affected subjects. We present the improved results for various classification algorithms, with AUROC values of best classification models at 0.99.

Download Full-text

A satellite-based spatio-temporal machine learning model to reconstruct daily PM2.5 concentrations across Great Britain

10.1101/2020.07.19.20157396 ◽

2020 ◽

Author(s):

Rochelle Schneider dos Santos ◽

Ana Vicedo-Cabrera ◽

Francesco Sera ◽

Massimo Stafoggia ◽

Kees de Hoogh ◽

...

Keyword(s):

Machine Learning ◽

Great Britain ◽

Temporal Resolution ◽

Fine Particulate Matter ◽

Epidemiological Studies ◽

Learning Model ◽

Additional Information ◽

Multi Stage ◽

Machine Learning Model ◽

Spatio Temporal

Epidemiological studies on health effects of air pollution usually rely on measurements from fixed ground monitors, which provide limited spatio-temporal coverage. Data from satellites, reanalysis and chemical transport models offer additional information used to reconstruct pollution concentrations at high spatio-temporal resolution. The aim of this study is to develop a multi-stage satellite-based machine learning model to estimate daily fine particulate matter (PM2.5) levels across Great Britain during 2008-2018. This high-resolution model consists of random forest (RF) algorithms applied in four stages. Stage-1 augments monitor-PM2.5 series using co-located PM10 measures. Stage-2 imputes missing satellite aerosol optical depth observations using atmospheric reanalysis models. Stage-3 integrates the output from previous stages with spatial and spatio-temporal variables to build a prediction model for PM2.5. Stage-4 applies Stage-3 models to estimate daily PM2.5 concentrations over a 1-km grid. The RF architecture performed well in all stages, with results from Stage-3 showing an average cross-validated R2 of 0.767 and minimal bias. The model performed better over the temporal scale when compared to the spatial component, but both presented good accuracy with an R2 of 0.795 and 0.658, respectively. The high spatio-temporal resolution and relatively high precision allows this dataset (approximately 950 million points) to be used in epidemiological analyses to assess health risks associated with both short- and long-term exposures to PM2.5.

Download Full-text

Evaluations of Machine Learning-Based CYGNSS Soil Moisture Estimates against SMAP Observations

Remote Sensing ◽

10.3390/rs12213503 ◽

2020 ◽

Vol 12 (21) ◽

pp. 3503 ◽

Cited By ~ 1

Author(s):

Volkan Senyurek ◽

Fangni Lei ◽

Dylan Boyd ◽

Ali Cafer Gurbuz ◽

Mehmet Kurum ◽

...

Keyword(s):

Machine Learning ◽

Soil Moisture ◽

Correlation Coefficient ◽

Root Mean Square ◽

Temporal Resolution ◽

Mean Square ◽

In Situ Observations ◽

Spatio Temporal ◽

Mean Square Errors

This paper presents a machine learning (ML) framework to derive a quasi-global soil moisture (SM) product by direct use of the Cyclone Global Navigation Satellite System (CYGNSS)’s high spatio-temporal resolution observations over the tropics (within ±38° latitudes) at L-band. The learning model is trained by using in-situ SM data from the International Soil Moisture Network (ISMN) sites and various space-borne ancillary data. The approach produces daily SM retrievals that are gridded to 3 km and 9 km within the CYGNSS spatial coverage. The performance of the model is independently evaluated at various temporal scales (daily, 3-day, weekly, and monthly) against Soil Moisture Active Passive (SMAP) mission’s enhanced SM products at a resolution of 9 km × 9 km. The mean unbiased root-mean-square difference (ubRMSD) between concurrent (same calendar day) CYGNSS and SMAP SM retrievals for about three years (from 2017 to 2019) is 0.044 cm3 cm−3 with a correlation coefficient of 0.66 over SMAP recommended grids. The performance gradually improves with temporal averaging and degrades over regions regularly flagged by SMAP such as dense forest, high topography, and coastlines. Furthermore, CYGNSS and SMAP retrievals are evaluated against 170 ISMN in-situ observations that result in mean unbiased root-mean-square errors (ubRMSE) of 0.055 cm3 cm−3 and 0.054 cm3 cm−3, respectively, and a higher correlation coefficient with CYGNSS retrievals. It is important to note that the proposed approach is trained over limited in-situ observations and is independent of SMAP observations in its training. The retrieval performance indicates current applicability and future growth potential of GNSS-R-based, directly measured spaceborne SM products that can provide improved spatio-temporal resolution than currently available datasets.

Download Full-text

Spatio-Temporal Classification and Prediction of Land Use and Land Cover Change for the Vembanad Lake System, Kerala – a Machine Learning Approach

10.21203/rs.3.rs-581788/v1 ◽

2021 ◽

Author(s):

Parthasarathy Kulithalai Shiyam Sundar ◽

Paresh Chandra Deka

Keyword(s):

Machine Learning ◽

Land Use ◽

Land Cover ◽

Google Earth ◽

Anthropogenic Activity ◽

Support Vector ◽

Learning Approaches ◽

Barren Land ◽

Lake System ◽

Spatio Temporal

Abstract Land use and land cover (LULC) change has become a critical issue for decision planners and conservationists due to inappropriate growth and its effect on natural ecosystems. As a result, the goal of this study is to identify the LULC for the Vembanad Lake System (VLS), Kerala in the short term, i.e., within a decade, utilizing two standard machine learning approaches, Random Forest (RF) and Support Vector Machines (SVM), on the Google Earth Engine (GEE) platform. When comparing the two techniques, SVM is classified at an average accuracy of around 84.5%, while RF is classified at 89%. The RF outperformed the SVM in almost identical spectral classes such as barren land and built-up areas. As a result, RF classified LULC is considered to predict the Spatio-temporal distribution of LULC transition analysis for 2035 and 2050. The study was conducted in Idrisi TerrSet software using the Cellular Automata (CA)-Markov chain analysis. The model's efficiency is evaluated by comparing the projected 2019 image to the actual 2019 classified image. The efficiency was good with more than 94% accuracy for the classes except for barren land, which might have resulted from the recent natural calamities and the accelerated anthropogenic activity in the area.

Download Full-text

A Machine Learning Based Downscaling Approach to Produce High Spatio-Temporal Resolution Land Surface Temperature of the Antarctic Dry Valleys from MODIS Data

Remote Sensing ◽

10.3390/rs13224673 ◽

2021 ◽

Vol 13 (22) ◽

pp. 4673

Author(s):

Lilian-Maite Lezama Valdes ◽

Marwan Katurji ◽

Hanna Meyer

Keyword(s):

Machine Learning ◽

Surface Temperature ◽

Spatial Resolution ◽

Temporal Resolution ◽

Land Surface Temperature ◽

Land Surface ◽

Moisture Distribution ◽

Dry Valleys ◽

Spatio Temporal ◽

The Antarctic

To monitor environmental and biological processes, Land Surface Temperature (LST) is a central variable, which is highly variable in space and time. This particularly applies to the Antarctic Dry Valleys, which host an ecosystem highly adapted to the extreme conditions in this cold desert. To predict possible climate induced changes on the Dry Valley ecosystem, high spatial and temporal resolution environmental variables are needed. Thus we enhanced the spatial resolution of the MODIS satellite LST product that is sensed sub-daily at a 1 km spatial resolution to a 30 m spatial resolution. We employed machine learning models that are trained using Landsat 8 thermal infrared data from 2013 to 2019 as a reference to predict LST at 30 m resolution. For the downscaling procedure, terrain derived variables and information on the soil type as well as the solar insolation were used as potential predictors in addition to MODIS LST. The trained model can be applied to all available MODIS scenes from 1999 onward to develop a 30 m resolution LST product of the Antarctic Dry Valleys. A spatio-temporal validation revealed an R2 of 0.78 and a RMSE of 3.32 ∘C. The downscaled LST will provide a valuable surface climate data set for various research applications, such as species distribution modeling, climate model evaluation, and the basis for the development of further relevant environmental information such as the surface moisture distribution.

Download Full-text