scholarly journals SPF ICE: A Novel Approach to Predict the Optimal Amount of Silica to Preserve Glaciers Using Reinforcement Learning

2021 ◽  
Author(s):  
Aadhav Prabu
Keyword(s):  
Reinforcement Learning ◽  
Low Cost ◽  
Arctic Sea Ice ◽  
The Arctic ◽  
Sea Levels ◽  
Optimal Amount ◽  
Novel Approach ◽  
The Pacific ◽  
Glacier Melting ◽  
Climate Crisis

<div><div><div><p>Glaciers cover nearly 10 percent of the earth’s surface but are melting at an inexorable rate. According to the pacific standard magazine, the Arctic sea ice has lost 80 percent of its volume since 1979. Antarctica’s ’Doomsday Glacier’ is melting faster and could raise global sea levels by two feet. As three-quarters of the earth’s freshwater is stored in glaciers, its melting depletes freshwater resources for millions of people. Glaciers also play a huge role in the climate crisis. Preserving glaciers is an important and imminent solution to save our planet. Silica microspheres are promising materials to prevent glacier melting as it reflects most of the sun’s radiation. When spread in layers over the glacier, it can slow the rate of melt and aid in new ice formation. However, if not used precisely, silica can be ineffective and expensive. SPF ICE is a novel method implemented to effectively de- termine the optimal amount of silica based on glacier’s properties to prevent its depletion substantially using reinforcement learning agents and a custom OpenAI Gym environment. The environment simulates a real-world model of a glacial setting using specific data, such as the glacier’s mass balance, tem- perature, and average accumulation and ablation. After testing the agents during many episodes, my solution reduced glacial melting by an average of 60.40% using the optimal amount of Silica. Additionally, this solution is customizable for any type of glacier. SPF ICE is an efficient and low-cost solution to curb glacier melting to preserve planet earth.</p></div></div></div>

scholarly journals SPF ICE: A Novel Approach to Predict the Optimal Amount of Silica to Preserve Glaciers Using Reinforcement Learning

2021 ◽  
Author(s):  
Aadhav Prabu
Keyword(s):  
Reinforcement Learning ◽  
Low Cost ◽  
Arctic Sea Ice ◽  
The Arctic ◽  
Sea Levels ◽  
Optimal Amount ◽  
Novel Approach ◽  
The Pacific ◽  
Glacier Melting ◽  
Climate Crisis

<div><div><div><p>Glaciers cover nearly 10 percent of the earth’s surface but are melting at an inexorable rate. According to the pacific standard magazine, the Arctic sea ice has lost 80 percent of its volume since 1979. Antarctica’s ’Doomsday Glacier’ is melting faster and could raise global sea levels by two feet. As three-quarters of the earth’s freshwater is stored in glaciers, its melting depletes freshwater resources for millions of people. Glaciers also play a huge role in the climate crisis. Preserving glaciers is an important and imminent solution to save our planet. Silica microspheres are promising materials to prevent glacier melting as it reflects most of the sun’s radiation. When spread in layers over the glacier, it can slow the rate of melt and aid in new ice formation. However, if not used precisely, silica can be ineffective and expensive. SPF ICE is a novel method implemented to effectively de- termine the optimal amount of silica based on glacier’s properties to prevent its depletion substantially using reinforcement learning agents and a custom OpenAI Gym environment. The environment simulates a real-world model of a glacial setting using specific data, such as the glacier’s mass balance, tem- perature, and average accumulation and ablation. After testing the agents during many episodes, my solution reduced glacial melting by an average of 60.40% using the optimal amount of Silica. Additionally, this solution is customizable for any type of glacier. SPF ICE is an efficient and low-cost solution to curb glacier melting to preserve planet earth.</p></div></div></div>

scholarly journals SPF ICE: A Novel Approach to Model the Amount And Effectiveness of Silica to Preserve Glaciers Using Reinforcement Learning

2021 ◽  
Author(s):  
Aadhav Prabu
Keyword(s):  
Reinforcement Learning ◽  
Cost Effective ◽  
Arctic Sea Ice ◽  
The Arctic ◽  
Sea Levels ◽  
Optimal Amount ◽  
Novel Approach ◽  
The Pacific ◽  
Glacier Melting ◽  
Climate Crisis

<p>Glaciers cover nearly 10 percent of the earth’s surface but are melting at an inexorable rate. According to the Pacific Standard magazine, the Arctic Sea ice has lost 80 percent of its volume since 1979. Antarctica’s ’Doomsday Glacier’ is melting faster and could raise global sea levels by two feet. As three-quarters of the earth’s fresh water is stored in glaciers, its melting depletes freshwater resources for millions of people. Glaciers also play a huge role in the climate crisis. Silica microspheres are promising materials to prevent glacier melting as it reflects most of the sun’s radiation. When spread in layers over the glacier, it can slow the rate of melt and aid in new ice formation. However, it is necessary to determine the ideal amount of silica to achieve the desired result with minimum environmental impact. This paper introduces a novel method SPF ICE to determine the optimal amount of silica based on glacier’s properties using reinforcement learning agents and a custom OpenAI Gym environment. The environment simulates a real-world model of a glacial setting using specific data, such as the glacier’s mass balance, temperature, and average accumulation and ablation. After testing the agents, the proposed solution reduced glacial melting by an average of 60.40% using the optimal amount of silica. The results indicate SPF ICE is a promising and cost-effective solution to curb glacier melting.<br></p>

scholarly journals SPF ICE: A Novel Approach to Predict the Optimal Amount of Silica to Preserve Glaciers Using Reinforcement Learning

2021 ◽  
Author(s):  
Aadhav Prabu
Keyword(s):  
Reinforcement Learning ◽  
Cost Effective ◽  
Arctic Sea Ice ◽  
The Arctic ◽  
Sea Levels ◽  
Optimal Amount ◽  
Novel Approach ◽  
The Pacific ◽  
Glacier Melting ◽  
Climate Crisis

<p>Glaciers cover nearly 10 percent of the earth’s surface but are melting at an inexorable rate. According to the Pacific Standard magazine, the Arctic Sea ice has lost 80 percent of its volume since 1979. Antarctica’s ’Doomsday Glacier’ is melting faster and could raise global sea levels by two feet. As three-quarters of the earth’s fresh water is stored in glaciers, its melting depletes freshwater resources for millions of people. Glaciers also play a huge role in the climate crisis. Silica microspheres are promising materials to prevent glacier melting as it reflects most of the sun’s radiation. When spread in layers over the glacier, it can slow the rate of melt and aid in new ice formation. However, it is necessary to determine the ideal amount of silica to achieve the desired result with minimum environmental impact. This paper introduces a novel method SPF ICE to determine the optimal amount of silica based on glacier’s properties using reinforcement learning agents and a custom OpenAI Gym environment. The environment simulates a real-world model of a glacial setting using specific data, such as the glacier’s mass balance, temperature, and average accumulation and ablation. After testing the agents, the proposed solution reduced glacial melting by an average of 60.40% using the optimal amount of silica. The results indicate SPF ICE is a promising and cost-effective solution to curb glacier melting.<br></p>

scholarly journals Record high Pacific Arctic seawater temperatures and delayed sea ice advance in response to episodic atmospheric blocking

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Tsubasa Kodaira ◽  
Takuji Waseda ◽  
Takehiko Nose ◽  
Jun Inoue
Keyword(s):  
Sea Ice ◽  
Arctic Region ◽  
Arctic Sea Ice ◽  
Sea Surface ◽  
The Arctic ◽  
Atmospheric Blocking ◽  
Sea Ice Extent ◽  
The Pacific ◽  
Arctic Sea ◽  
Highly Correlated

AbstractArctic sea ice is rapidly decreasing during the recent period of global warming. One of the significant factors of the Arctic sea ice loss is oceanic heat transport from lower latitudes. For months of sea ice formation, the variations in the sea surface temperature over the Pacific Arctic region were highly correlated with the Pacific Decadal Oscillation (PDO). However, the seasonal sea surface temperatures recorded their highest values in autumn 2018 when the PDO index was neutral. It is shown that the anomalous warm seawater was a rapid ocean response to the southerly winds associated with episodic atmospheric blocking over the Bering Sea in September 2018. This warm seawater was directly observed by the R/V Mirai Arctic Expedition in November 2018 to significantly delay the southward sea ice advance. If the atmospheric blocking forms during the PDO positive phase in the future, the annual maximum Arctic sea ice extent could be dramatically reduced.

Variability of Arctic Sea Ice Based on Quantile Regression and the Teleconnection with Large-Scale Climate Patterns

2020 ◽  
Vol 33 (10) ◽  
pp. 4009-4025
Author(s):  
Shuyu Zhang ◽  
Thian Yew Gan ◽  
Andrew B. G. Bush
Keyword(s):  
Sea Ice ◽  
Quantile Regression ◽  
Large Scale ◽  
Southern Oscillation ◽  
Arctic Sea Ice ◽  
The Arctic ◽  
Climate Indices ◽  
The Pacific ◽  
Arctic Sea ◽  
Climate Patterns

AbstractUnder global warming, Arctic sea ice has declined significantly in recent decades, with years of extremely low sea ice occurring more frequently. Recent studies suggest that teleconnections with large-scale climate patterns could induce the observed extreme sea ice loss. In this study, a probabilistic analysis of Arctic sea ice was conducted using quantile regression analysis with covariates, including time and climate indices. From temporal trends at quantile levels from 0.01 to 0.99, Arctic sea ice shows statistically significant decreases over all quantile levels, although of different magnitudes at different quantiles. At the representative extreme quantile levels of the 5th and 95th percentiles, the Arctic Oscillation (AO), the North Atlantic Oscillation (NAO), and the Pacific–North American pattern (PNA) have more significant influence on Arctic sea ice than El Niño–Southern Oscillation (ENSO), the Pacific decadal oscillation (PDO), and the Atlantic multidecadal oscillation (AMO). Positive AO as well as positive NAO contribute to low winter sea ice, and a positive PNA contributes to low summer Arctic sea ice. If, in addition to these conditions, there is concurrently positive AMO and PDO, the sea ice decrease is amplified. Teleconnections between Arctic sea ice and the climate patterns were demonstrated through a composite analysis of the climate variables. The anomalously strong anticyclonic circulation during the years of positive AO, NAO, and PNA promotes more sea ice export through Fram Strait, resulting in excessive sea ice loss. The probabilistic analyses of the teleconnections between the Arctic sea ice and climate patterns confirm the crucial role that the climate patterns and their combinations play in overall sea ice reduction, but particularly for the low and high quantiles of sea ice concentration.

scholarly journals Inter-Relations between the Arctic Sea Ice and the General Circulation of the Atmosphere (Abstract)

1987 ◽  
Vol 9 ◽  
pp. 252-252
Author(s):  
G. Wendler ◽  
M. Jeffries ◽  
Y. Nagashima
Keyword(s):  
Sea Ice ◽  
General Circulation ◽  
Arctic Sea Ice ◽  
The Arctic ◽  
Zonal Circulation ◽  
The Pacific ◽  
Arctic Sea ◽  
Ice Conditions ◽  
The Pacific Ocean ◽  
Opposing Effects

Satellite imagery has substantially improved the quality of sea-Ice observation over the last decades. Therefore, for a 25-year period, a statistical study based on the monthly Arctic sea-ice data and the monthly mean 700 mbar maps of the Northern Hemisphere was carried out to establish the relationships between sea-ice conditions and the general circulation of the atmosphere. It was found that sea-ice conditions have two opposing effects on the zonal circulation intensity, depending on the season. Heavier than normal ice in winter causes stronger than normal zonal circulation in the subsequent months, whereas heavier than normal ice in the summer–fall causes weaker zonal circulation in the subsequent months. Analyzing the two sectors, the Atlantic and Pacific ones separately, a negative correlation was found, which means a heavy ice year in the Atlantic Ocean is normally associated with a light one in the Pacific Ocean and vice versa.

Air-Sea Fluxes following the Unusually Early Ice Retreats in the Arctic

2020 ◽  
Author(s):  
Dongxiao Zhang ◽  
Chidong Zhang ◽  
Jessica Cross ◽  
Calvin Mordy ◽  
Edward Cokelet ◽  
...  
Keyword(s):  
Sea Ice ◽  
Numerical Models ◽  
Green Energy ◽  
Arctic Sea Ice ◽  
Heat Fluxes ◽  
The Arctic ◽  
Energy Fluxes ◽  
The Pacific ◽  
Arctic Sea ◽  
Ice Retreat

&lt;p&gt;The Arctic has been rapidly changing over the last decade, with more frequent unusually early ice retreats in late spring and summer. Vast Arctic areas that were usually covered by sea ice are now exposed to the atmosphere because of earlier ice retreat and later arrival. Assessment of consequential changes in the energy cycle of the Arctic and their potential feedback to the variability of Arctic sea ice and marine ecosystems critically depends on the accuracy of surface flux estimates. In the Pacific sector of the Arctic, earlier ice retreat generally follows the warm Pacific water inflow into the Arctic through the Bering and Chukchi Seas. Due to ice coverage and irregularity of seasonal ice retreats, air-sea flux measurements following the ice retreats has been difficult to plan and execute. A recent technology development is the Unmanned Surface Vehicles (USVs): The long-range USV saildrones are powered by green energy with wind for propulsion and solar energy for instrumentation and vehicle control. NOAA/PMEL and University of Washington scientists have made surface measurements of the ocean and atmosphere in the Pacific Arctic using saildrones for the past several years. In 2019, for the 1&lt;sup&gt;st&lt;/sup&gt; time a fleet of six saildrones capable of measuring both turbulent and radiative heat fluxes, wind stress, air-sea CO&lt;sub&gt;2&lt;/sub&gt; flux and upper ocean currents was deployed to follow the ice retreat from May to October, with five of the USVs into the Chukchi and Beaufort Seas while one staying in the Bering Sea. These in situ measurements provide rare opportunities of estimating air-sea energy fluxes during a period of rapid reduction in Arctic sea ice in different scenarios: open water after ice melt, free-floating ice bands, and marginal ice zones. In this study, Arctic air-sea heat and momentum fluxes measured by the saildrones are compared to gridded flux products based on satellite data and numerical models to investigate the circumstances under which they agree and differ, and the main sources of their discrepancies. The results will quantify the uncertainty margins in the gridded flux products and provide insights needed to improve their accuracy. We will also discuss the feasibility of using USVs in sustained Arctic observing system to collect benchmark datasets of the changing surface energy fluxes due to rapid sea ice reduction and provide real time data for improved weather and ocean forecasts.&amp;#160;&amp;#160;&lt;/p&gt;

Speleothem record of enhanced hydroclimate during MIS15a in Northeast Greenland

2020 ◽  
Author(s):  
Gina Moseley ◽  
R. Lawrence Edwards ◽  
Christoph Spötl ◽  
Hai Cheng
Keyword(s):  
Arctic Region ◽  
Arctic Sea Ice ◽  
The Arctic ◽  
Climate History ◽  
Sea Levels ◽  
Temperature And Precipitation ◽  
Arctic Sea ◽  
History Of ◽  
Forcing Mechanisms ◽  
Essential Knowledge

&lt;p&gt;The Arctic region is predicted to be one of the most sensitive areas of the world to future anthropogenically-forced climate change, the consequences of which will affect vast numbers of people worldwide, for instance through changes to mid-latitude weather systems and rising eustatic sea levels. Recent changes in temperature and precipitation, and those projected for the future, indicate that some of the greatest changes will occur in Northeast Greenland. Essential knowledge on the climate history of this region, which can be used to validate models and understand forcing mechanisms and teleconnections, is however absent. Here, we present a speleothem palaeoclimate record for Northeast Greenland (80 &amp;#176;N) that formed during Marine Isotopes Stage 15a&amp;#160; between 588 ka to 537 ka. The record indicates that at that time, Northeast Greenland was warmer and wetter than at present associated with a reduction in Arctic sea ice, thawing of permafrost in eastern Siberia (55 &amp;#176;N and 60 &amp;#176;N), and elevated warm conditions at Lake El&amp;#8217;gygytgyn (67.5 &amp;#176;N), Russia.&lt;/p&gt;

Predictable Patterns of Wintertime Surface Air Temperature in Northern Hemisphere and Their Predictability Sources in the SEAS5

2020 ◽  
Vol 33 (24) ◽  
pp. 10743-10754
Author(s):  
Hongdou Fan ◽  
Lin Wang ◽  
Yang Zhang ◽  
Youmin Tang ◽  
Wansuo Duan ◽  
...  
Keyword(s):  
North America ◽  
Northern Hemisphere ◽  
Air Temperature ◽  
Southern Oscillation ◽  
Arctic Sea Ice ◽  
Prediction Skill ◽  
The Arctic ◽  
The Tibetan Plateau ◽  
Central Pacific ◽  
The Pacific

AbstractBased on 36-yr hindcasts from the fifth-generation seasonal forecast system of the European Centre for Medium-Range Weather Forecasts (SEAS5), the most predictable patterns of the wintertime 2-m air temperature (T2m) in the extratropical Northern Hemisphere are extracted via the maximum signal-to-noise (MSN) empirical orthogonal function (EOF) analysis, and their associated predictability sources are identified. The MSN EOF1 captures the warming trend that amplifies over the Arctic but misses the associated warm Arctic–cold continent pattern. The MSN EOF2 delineates a wavelike T2m pattern over the Pacific–North America region, which is rooted in the tropical forcing of the eastern Pacific-type El Niño–Southern Oscillation (ENSO). The MSN EOF3 shows a wavelike T2m pattern over the Pacific–North America region, which has an approximately 90° phase difference from that associated with MSN EOF2, and a loading center over midlatitude Eurasia. Its sources of predictability include the central Pacific-type ENSO and Eurasian snow cover. The MSN EOF4 reflects T2m variability surrounding the Tibetan Plateau, which is plausibly linked to the remote forcing of the Arctic sea ice. The information on the leading predictable patterns and their sources of predictability is further used to develop a calibration scheme to improve the prediction skill of T2m. The calibrated prediction skill in terms of the anomaly correlation coefficient improves significantly over midlatitude Eurasia in a leave-one-out cross-validation, implying a possible way to improve the wintertime T2m prediction in the SEAS5.

Atmospheric and oceanic drivers of regional Arctic winter sea-ice variability in present and future climates

2021 ◽  
Author(s):  
Jakob Dörr ◽  
Marius Årthun ◽  
Tor Eldevik ◽  
Erica Madonna
Keyword(s):  
Sea Ice ◽  
Arctic Ocean ◽  
Heat Transport ◽  
Barents Sea ◽  
Arctic Sea Ice ◽  
The Arctic ◽  
Ocean Heat Transport ◽  
The Pacific ◽  
Arctic Sea ◽  
The Arctic Ocean

&lt;p&gt;The recent retreat of Arctic sea ice area is overlaid by strong internal variability on all timescales. In winter, sea ice retreat and variability are currently dominated by the Barents Sea, primarily driven by variable ocean heat transport from the Atlantic. Climate models from the latest intercomparison project CMIP6 project that the future loss of winter Arctic sea ice spreads throughout the Arctic Ocean and, hence, that other regions of the Arctic Ocean will see increased sea-ice variability. It is, however, not known how the influence of ocean heat transport will change, and to what extent and in which regions other drivers, such as atmospheric circulation or river runoff into the Arctic Ocean, will become important. Using a combination of observations and simulations from the Community Earth System Model Large Ensemble (CESM-LE), we analyze and contrast the present and future regional drivers of the variability of the winter Arctic sea ice cover. We find that for the recent past, both observations and CESM-LE show that sea ice variability in the Atlantic and Pacific sector of the Arctic Ocean is influenced by ocean heat transport through the Barents Sea and Bering Strait, respectively. The two dominant modes of large-scale atmospheric variability &amp;#8211; the Arctic Oscillation and the Pacific North American pattern &amp;#8211; are only weakly related to recent regional sea ice variability. However, atmospheric circulation anomalies associated with regional sea ice variability show distinct patterns for the Atlantic and Pacific sectors consistent with heat and humidity transport from lower latitudes. In the future, under a high emission scenario, CESM-LE projects a gradual expansion of the footprint of the Pacific and Atlantic inflows, covering the whole Arctic Ocean by 2050-2079. This study highlights the combined importance of future Atlantification and Pacification of the Arctic Ocean and improves our understanding of internal climate variability which essential in order to predict future sea ice changes under anthropogenic warming.&amp;#160; &amp;#160;&lt;/p&gt;&lt;p&gt;&amp;#160;&lt;/p&gt;

Sign in / Sign up

Export Citation Format

Share Document