scholarly journals Spatial-Temporal Distribution of the Freeze–Thaw Cycle of the Largest Lake (Qinghai Lake) in China Based on Machine Learning and MODIS from 2000 to 2020

2021 ◽  
Vol 13 (9) ◽  
pp. 1695
Author(s):  
Weixiao Han ◽  
Chunlin Huang ◽  
Juan Gu ◽  
Jinliang Hou ◽  
Ying Zhang
Keyword(s):  
Machine Learning ◽  
Land Surface ◽  
Temporal Dynamics ◽  
Temporal Distribution ◽  
Ice Cover ◽  
Qinghai Lake ◽  
Gap Filling ◽  
Thaw Cycle ◽  
Break Up ◽  
Ice Phenology

The lake ice phenology variations are vital for the land–surface–water cycle. Qinghai Lake is experiencing amplified warming under climate change. Based on the MODIS imagery, the spatio-temporal dynamics of the ice phenology of Qinghai Lake were analyzed using machine learning during the 2000/2001 to 2019/2020 ice season, and cloud gap-filling procedures were applied to reconstruct the result. The results showed that the overall accuracy of the water–ice classification by random forest and cloud gap-filling procedures was 98.36% and 92.56%, respectively. The annual spatial distribution of the freeze-up and break-up dates ranged primarily from DOY 330 to 397 and from DOY 70 to 116. Meanwhile, the decrease rates of freeze-up duration (DFU), full ice cover duration (DFI), and ice cover duration (DI) were 0.37, 0.34, and 0.13 days/yr., respectively, and the duration was shortened by 7.4, 6.8, and 2.6 days over the past 20 years. The increased rate of break-up duration (DBU) was 0.58 days/yr. and the duration was lengthened by 11.6 days. Furthermore, the increase in temperature resulted in an increase in precipitation after two years; the increase in precipitation resulted in the increase in DBU and decrease in DFU in corresponding years, and decreased DI and DFI after one year.

Lake ice phenology changes in the northern hemisphere

2021 ◽  
Author(s):  
Yubao Qiu ◽  
Xingxing Wang ◽  
Matti Leppäranta ◽  
Bin Cheng ◽  
Yixiao Zhang
Keyword(s):  
Remote Sensing ◽  
North America ◽  
Northern Hemisphere ◽  
Ice Cover ◽  
Passive Microwave ◽  
Lake Area ◽  
Lake Ice ◽  
Northern Tibetan Plateau ◽  
Break Up ◽  
Ice Phenology

<p>Lake-ice phenology is an essential indicator of climate change impact for different regions (Livingstone, 1997; Duguay, 2010), which helps understand the regional characters of synchrony and asynchrony. The observation of lake ice phenology includes ground observation and remote sensing inversion. Although some lakes have been observed for hundreds of years, due to the limitations of the observation station and the experience of the observers, ground observations cannot obtain the lake ice phenology of the entire lake. Remote sensing has been used for the past 40 years, in particular, has provided data covering the high mountain and high latitude regions, where the environment is harsh and ground observations are lacking. Remote sensing also provides a unified data source and monitoring standard, and the possibility of monitoring changes in lake ice in different regions and making comparisons between them. The existing remote sensing retrieval products mainly cover North America and Europe, and data for Eurasia is lacking (Crétaux et al., 2020).</p><p>Based on the passive microwave, the lake ice phenology of 522 lakes in the northern hemisphere during 1978-2020 was obtained, including Freeze-Up Start (FUS), Freeze-Up End (FUE), Break-Up Start (BUS), Break-Up End (BUE), and Ice Cover Duration (ICD). The ICD is the duration from the FUS to the BUE, which can directly reflect the ice cover condition. At latitudes north of 60°N, the average of ICD is approximately 8-9 months in North America and 5-6 months in Eurasia. Limited by the spatial resolution of the passive microwave, lake ice monitoring is mainly in Northern Europe. Therefore, the average of ICD over Eurasia is shorter, while the ICD is more than 6 months for most lakes in Russia. After 2000, the ICD has shown a shrinking trend, except northeastern North America (southeast of the Hudson Bay) and the northern Tibetan Plateau. The reasons for the extension of ice cover duration need to be analyzed with parameters, such as temperature, the lake area, and lake depth, in the two regions.</p>

scholarly journals Lake Phenology of Freeze-Thaw Cycles Using Random Forest: A Case Study of Qinghai Lake

2020 ◽  
Vol 12 (24) ◽  
pp. 4098
Author(s):  
Weixiao Han ◽  
Chunlin Huang ◽  
Hongtao Duan ◽  
Juan Gu ◽  
Jinliang Hou
Keyword(s):  
Surface Water ◽  
Random Forest ◽  
Surface Temperature ◽  
Land Surface Temperature ◽  
Land Surface ◽  
Qinghai Lake ◽  
Water Index ◽  
Freeze Thaw ◽  
Normalized Difference Water Index ◽  
Break Up

Lake phenology is essential for understanding the lake freeze-thaw cycle effects on terrestrial hydrological processes. The Qinghai-Tibetan Plateau (QTP) has the most extensive ice reserve outside of the Arctic and Antarctic poles and is a sensitive indicator of global climate changes. Qinghai Lake, the largest lake in the QTP, plays a critical role in climate change. The freeze-thaw cycles of lakes were studied using daily Moderate Resolution Imaging Spectroradiometer (MODIS) data ranging from 2000–2018 in the Google Earth Engine (GEE) platform. Surface water/ice area, coverage, critical dates, surface water, and ice cover duration were extracted. Random forest (RF) was applied with a classifier accuracy of 0.9965 and a validation accuracy of 0.8072. Compared with six common water indexes (tasseled cap wetness (TCW), normalized difference water index (NDWI), modified normalized difference water index (MNDWI), automated water extraction index (AWEI), water index 2015 (WI2015) and multiband water index (MBWI)) and ice threshold value methods, the critical freeze-up start (FUS), freeze-up end (FUE), break-up start (BUS), and break-up end (BUE) dates were extracted by RF and validated by visual interpretation. The results showed an R2 of 0.99, RMSE of 3.81 days, FUS and BUS overestimations of 2.50 days, and FUE and BUE underestimations of 0.85 days. RF performed well for lake freeze-thaw cycles. From 2000 to 2018, the FUS and FUE dates were delayed by 11.21 and 8.21 days, respectively, and the BUS and BUE dates were 8.59 and 1.26 days early, respectively. Two novel key indicators, namely date of the first negative land surface temperature (DFNLST) and date of the first positive land surface temperature (DFPLST), were proposed to comprehensively delineate lake phenology: DFNLST was approximately 37 days before FUS, and DFPLST was approximately 20 days before BUS, revealing that the first negative and first positive land surface temperatures occur increasingly earlier.

scholarly journals Analysis of ice phenology of lakes on the Tibetan Plateau from MODIS data

2013 ◽  
Vol 7 (1) ◽  
pp. 287-301 ◽  
Author(s):  
J. Kropáček ◽  
F. Maussion ◽  
F. Chen ◽  
S. Hoerz ◽  
V. Hochschild
Keyword(s):  
Tibetan Plateau ◽  
Ice Cover ◽  
Optical Data ◽  
Water Volume ◽  
The Tibetan Plateau ◽  
Large Lakes ◽  
Local Conditions ◽  
Mean Values ◽  
Break Up ◽  
Ice Phenology

Abstract. The Tibetan Plateau includes a large system of endorheic (closed basin) lakes. Lake ice phenology, i.e. the timing of freeze-up and break-up and the duration of the ice cover may provide valuable information about climate variations in this region. The ice phenology of 59 large lakes on the Tibetan Plateau was derived from Moderate Resolution Imaging Spectroradiometer (MODIS) 8-day composite data for the period from 2001 to 2010. Ice cover duration appears to have a high variability in the studied region due to both climatic and local factors. Mean values for the duration of ice cover were calculated for three groups of lakes defined by clustering, resulting in relatively compact geographic regions. In each group several lakes showed anomalies in ice cover duration in the studied period. Possible reasons for such anomalous behaviour are discussed. Furthermore, many lakes do not freeze up completely during some seasons. This was confirmed by inspection of high resolution optical data. Mild winter seasons, large water volume and/or high salinity are the most likely explanations. Trends in the ice cover duration derived by linear regression for all the studied lakes show a high variation in space. A correlation of ice phenology variables with parameters describing climatic and local conditions showed a high thermal dependency of the ice regime. It appears that the freeze-up tends to be more thermally determined than break-up for the studied lakes.

scholarly journals Monitoring the Ice Phenology of Qinghai Lake from 1980 to 2018 Using Multisource Remote Sensing Data and Google Earth Engine

2020 ◽  
Vol 12 (14) ◽  
pp. 2217 ◽  
Author(s):  
Miaomiao Qi ◽  
Shiyin Liu ◽  
Xiaojun Yao ◽  
Fuming Xie ◽  
Yongpeng Gao
Keyword(s):  
Google Earth ◽  
Qinghai Lake ◽  
Small Scale ◽  
Surface Reflectance ◽  
Lake Area ◽  
Lake Ice ◽  
Noaa Avhrr ◽  
Break Up ◽  
Freeze Duration ◽  
Ice Phenology

Lake ice, one of the most direct lake physical characteristics affected by climate change, can reflect small-scale environmental changes caused by the atmosphere and hydrology, as well as large-scale climate changes such as global warming. This study uses National Oceanic and Atmospheric Administration, Advanced Very High Resolution Radiometer (NOAA AVHRR), MOD09GQ surface reflectance products, and Landsat surface reflectance Tier 1 products, which comprehensively used RS and GIS technology to study lake ice phenology (LIP) and changes in Qinghai Lake. Over the past 38 years, freeze-up start and freeze-up end dates were gradually delayed by a rate of 0.16 d/a and 0.19 d/a, respectively, with a total delay by 6.08 d and 7.22 d. The dates of break-up start and break-up end showed advancing trends by −0.36 d/a and −0.42 d/a, respectively, which shifted them earlier by 13.68 d and 15.96 d. Overall, ice coverage duration, freeze duration, and complete freeze duration showed decreasing trends of −0.58 d/a, −0.60 d/a, and −0.52 d/a, respectively, and overall decreased by 22.04 d, 22.81 d, and 9.76 d between 1980 and 2018. The spatial pattern in the freeze–thaw of Qinghai Lake can be divided into two areas; the west of the lake area has similar spatial patterns of freezing and ablation, while, in the east of the lake area, freezing and ablation patterns are opposite. Climate factors were closely related to LIP, especially the accumulated freezing degree-day (AFDD) from October to April of the following year. Furthermore, freeze-up start time was more sensitive to changes in wind speed and precipitation.

scholarly journals A Machine Learning Approach for Remote Sensing Data Gap-Filling with Open-Source Implementation: An Example Regarding Land Surface Temperature, Surface Albedo and NDVI

2020 ◽  
Vol 12 (23) ◽  
pp. 3865
Author(s):  
Mikhail Sarafanov ◽  
Eduard Kazakov ◽  
Nikolay O. Nikitin ◽  
Anna V. Kalyuzhnaya
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Time Series ◽  
Surface Temperature ◽  
Land Surface Temperature ◽  
Land Surface ◽  
Temporal Dynamics ◽  
Machine Learning Algorithms ◽  
Series Data ◽  
Terra Modis

Satellite remote sensing has now become a unique tool for continuous and predictable monitoring of geosystems at various scales, observing the dynamics of different geophysical parameters of the environment. One of the essential problems with most satellite environmental monitoring methods is their sensitivity to atmospheric conditions, in particular cloud cover, which leads to the loss of a significant part of data, especially at high latitudes, potentially reducing the quality of observation time series until it is useless. In this paper, we present a toolbox for filling gaps in remote sensing time-series data based on machine learning algorithms and spatio-temporal statistics. The first implemented procedure allows us to fill gaps based on spatial relationships between pixels, obtained from historical time-series. Then, the second procedure is dedicated to filling the remaining gaps based on the temporal dynamics of each pixel value. The algorithm was tested and verified on Sentinel-3 SLSTR and Terra MODIS land surface temperature data and under different geographical and seasonal conditions. As a result of validation, it was found that in most cases the error did not exceed 1 °C. The algorithm was also verified for gaps restoration in Terra MODIS derived normalized difference vegetation index and land surface broadband albedo datasets. The software implementation is Python-based and distributed under conditions of GNU GPL 3 license via public repository.

scholarly journals Some aspects of ice phenology on ponds in central Alaska, USA

2007 ◽  
Vol 46 ◽  
pp. 397-403 ◽  
Author(s):  
Martin O. Jeffries ◽  
Kim Morris
Keyword(s):  
Air Temperature ◽  
Ice Cover ◽  
Ice Thickness ◽  
Minor Role ◽  
Strongly Correlated ◽  
Break Up ◽  
Long Term Observation ◽  
Change In Mean ◽  
Ice Phenology

AbstractIce phenology (freeze-up, break-up and duration) was monitored for five seasons between autumn 2001 and spring 2006 at 11 small, shallow ponds in the boreal forest of central Alaska, USA. The sequence in which freeze-up (FU; day of 100% ice cover) and break-up (BU; day of zero ice cover) occurred at the 11 ponds showed moderately high to very high coherence each season. This was probably due to FU and BU being poorly correlated with pond morphometry (area, depth). BU is strongly correlated with April mean air temperature; a ±1˚C change in mean April air temperature is equivalent to a ±1.86 day change in BU. FU and air-temperature relationships are inconclusive, primarily because post-FU warm intervals in two autumns cause an anticorrelation between mean September air temperature and FU. Mean ice duration varies between 205 and 225 days, and is strongly correlated with maximum ice thickness through its effect on BU. A ±10mm change in maximum ice thickness will cause a ±0.6 day change in ice duration. Maximum ice thickness and ice composition (snow ice, congelation ice) also have a strong influence on break-up when all data from all ponds and all years are considered. The predictability of FU and BU sequence, the minor role of morphometry in FU and BU, the strong role of April mean air temperature in BU, and the role of maximum ice thickness in duration suggests that these ponds would be good sites for continued long-term observation of phenology and the influence of weather/climate variation and change, and for freeze-up/break-up process studies, particularly the role of ice composition and albedo.

Application of machine learning as a gap-filling tool for satellite land surface temperature

2021 ◽  
Author(s):  
Isaac Newton Buo ◽  
Valentina Sagris ◽  
Jaak Jaagus
Keyword(s):  
Machine Learning ◽  
Surface Temperature ◽  
Land Surface Temperature ◽  
Land Surface ◽  
Vegetation Index ◽  
Vegetation Indices ◽  
Surface Air Temperature ◽  
Measured Temperature ◽  
Gap Filling ◽  
Spatial Coverage

<p>The frequency of heatwave events has increased in recent decades because of global warming. Satellite observed Land Surface Temperature (LST) is a widely used parameter for assessing heatwaves. It provides a wide spatial coverage compared to surface air temperature measured at weather stations. However, LST quality is limited by cloud contamination. Because heatwaves have a limited temporal frame, having a full and cloud-free complement of LST for that period is necessary.  We explore gap filling of LST using other spatial features like land cover, elevation and vegetation indices in a machine learning approach. We use a seamless open and free daily vegetation index  product which is paramount to the success of our study.  We create a Random Forest model that provides a ranking of features relevant for predicting LST. Our model is used in filling gaps in Moderate Resolution Imaging Spectroradiometer (MODIS) over three heat wave periods in different summers in Estonia. We compare the output of our model to an established spatiotemporal gap filling algorithm and with in-situ measured temperature to validate the predictive capability of our model. Our findings validate machine learning as a suitable tool for filling gaps in satellite LST and very useful when short time frames are of interest. In addition, we acknowledge that while time is an important factor in predicting LST, additional information on vegetation can improve the predictions of a model.</p>

scholarly journals Long-term changes of Daugava River ice phenology under the impact of the cascade of hydro power plants

2016 ◽  
Vol 70 (2) ◽  
pp. 71-77
Author(s):  
Elga Apsîte ◽  
Didzis Elferts ◽  
Inese Latkovska
Keyword(s):  
Power Plants ◽  
Ice Cover ◽  
River Ice ◽  
Hydro Power ◽  
Long Term Changes ◽  
Break Up ◽  
Hydro Power Plants ◽  
The Impact ◽  
Ice Phenology

Abstract This paper presents the results of the study of long-term changes of Daugava River ice phenology, i.e. the freeze-up date, the break-up date, and the duration of ice cover from 1919/1920 to 2011/2012, under the impact of the cascade of hydro power plants. The long-term changes of ice phenology were determined by global climate warming at the turn of the 20th and the 21st centuries and anthropogenic activities after the year 1939. The Mann-Kendall test showed that the ice freeze-up date has a positive trend, while the ice break-up date and the duration of ice cover had negative trends. The changes were statistically significant. Data series covering twenty years before and after construction of the hydro power plants were used for assessing the impact of each hydro power plant on changes of Daugava River ice phenology parameters. The study results showed that the duration of ice cover was significantly longer in water reservoirs, i.e. the freeze-up date was earlier and the break-up date was later. Downstream of dams duration of ice cover was shorter with later freeze-up dates and earlier break-up dates. The impact of hydro power plants on ice phenology parameters gradually decreased with distance down from the dams.

Sign in / Sign up

Export Citation Format

Share Document