scholarly journals Future Runoff Analysis in the Mekong River Basin under a Climate Change Scenario Using Deep Learning

Water ◽  
2020 ◽  
Vol 12 (6) ◽  
pp. 1556 ◽  
Author(s):  
Daeeop Lee ◽  
Giha Lee ◽  
Seongwon Kim ◽  
Sungho Jung

In establishing adequate climate change policies regarding water resource development and management, the most essential step is performing a rainfall-runoff analysis. To this end, although several physical models have been developed and tested in many studies, they require a complex grid-based parameterization that uses climate, topography, land-use, and geology data to simulate spatiotemporal runoff. Furthermore, physical rainfall-runoff models also suffer from uncertainty originating from insufficient data quality and quantity, unreliable parameters, and imperfect model structures. As an alternative, this study proposes a rainfall-runoff analysis system for the Kratie station on the Mekong River mainstream using the long short-term memory (LSTM) model, a data-based black-box method. Future runoff variations were simulated by applying a climate change scenario. To assess the applicability of the LSTM model, its result was compared with a runoff analysis using the Soil and Water Assessment Tool (SWAT) model. The following steps (dataset periods in parentheses) were carried out within the SWAT approach: parameter correction (2000–2005), verification (2006–2007), and prediction (2008–2100), while the LSTM model went through the process of training (1980–2005), verification (2006–2007), and prediction (2008–2100). Globally available data were fed into the algorithms, with the exception of the observed discharge and temperature data, which could not be acquired. The bias-corrected Representative Concentration Pathways (RCPs) 4.5 and 8.5 climate change scenarios were used to predict future runoff. When the reproducibility at the Kratie station for the verification period of the two models (2006–2007) was evaluated, the SWAT model showed a Nash–Sutcliffe efficiency (NSE) value of 0.84, while the LSTM model showed a higher accuracy, NSE = 0.99. The trend analysis result of the runoff prediction for the Kratie station over the 2008–2100 period did not show a statistically significant trend for neither scenario nor model. However, both models found that the annual mean flow rate in the RCP 8.5 scenario showed greater variability than in the RCP 4.5 scenario. These findings confirm that the LSTM runoff prediction presents a higher reproducibility than that of the SWAT model in simulating runoff variation according to time-series changes. Therefore, the LSTM model, which derives relatively accurate results with a small amount of data, is an effective approach to large-scale hydrologic modeling when only runoff time-series are available.

2009 ◽  
Vol 1 (1) ◽  
pp. 77-90 ◽  
Author(s):  
Marian Melo ◽  
Milan Lapin ◽  
Ingrid Damborska

Abstract In this paper methods of climate-change scenario projection in Slovakia for the 21st century are outlined. Temperature and precipitation time series of the Hurbanovo Observatory in 1871-2007 (Slovak Hydrometeorological Institute) and data from four global GCMs (GISS 1998, CGCM1, CGCM2, HadCM3) are utilized for the design of climate change scenarios. Selected results of different climate change scenarios (based on different methods) for the region of Slovakia (up to 2100) are presented. The increase in annual mean temperature is about 3°C, though the results are ambiguous in the case of precipitation. These scenarios are required by users in impact studies, mainly from the hydrology, agriculture and forestry sectors.


2011 ◽  
Vol 62 (9) ◽  
pp. 1043 ◽  
Author(s):  
Nick Bond ◽  
Jim Thomson ◽  
Paul Reich ◽  
Janet Stein

There are few quantitative predictions for the impacts of climate change on freshwater fish in Australia. We developed species distribution models (SDMs) linking historical fish distributions for 43 species from Victorian streams to a suite of hydro-climatic and catchment predictors, and applied these models to explore predicted range shifts under future climate-change scenarios. Here, we present summary results for the 43 species, together with a more detailed analysis for a subset of species with distinct distributions in relation to temperature and hydrology. Range shifts increased from the lower to upper climate-change scenarios, with most species predicted to undergo some degree of range shift. Changes in total occupancy ranged from –38% to +63% under the lower climate-change scenario to –47% to +182% under the upper climate-change scenario. We do, however, caution that range expansions are more putative than range contractions, because the effects of barriers, limited dispersal and potential life-history factors are likely to exclude some areas from being colonised. As well as potentially informing more mechanistic modelling approaches, quantitative predictions such as these should be seen as representing hypotheses to be tested and discussed, and should be valuable for informing long-term strategies to protect aquatic biota.


2017 ◽  
Vol 19 (3) ◽  
pp. 163 ◽  
Author(s):  
Adjie Pamungkas ◽  
Sarah Bekessy ◽  
Ruth Lane

Reducing community vulnerability to flooding is increasingly important given predicted intensive flood events in many parts of the world. We built a community vulnerability model to explore the effectiveness of a range of proactive and reactive adaptations to reduce community vulnerability to flood. The model consists of floods, victims, housings, responses, savings, expenditure and income sub models. We explore the robustness of adaptations under current conditions and under a range of future climate change scenarios. We present results of this model for a case study of Centini Village in Lamongan Municipality, Indonesia, which is highly vulnerable to the impacts of annual small-scale and infrequent extreme floods.  We compare 11 proactive adaptations using indicators of victims, damage/losses and recovery process to reflect the level of vulnerability. We find that reforestation and flood infrastructure redevelopment are the most effective proactive adaptations for minimising vulnerability to flood under current condition. Under climate change scenario, the floods are predicted to increase 17% on the average and 5% on the maximum measurements. The increasing floods result reforestation is the only effective adaptations in the future under climate change scenario.


2017 ◽  
Author(s):  
Sangchul Lee ◽  
In-Young Yeo ◽  
Ali M. Sadeghi ◽  
Gregory W. McCarty ◽  
Wells D. Hively ◽  
...  

Abstract. Water quality problems in the Chesapeake Bay Watershed (CBW) are expected to exacerbate under climate variability and change. However, climate impacts on agricultural lands and resultant nutrient loads into surface water resources are largely unknown. This study evaluates the impacts of climate variability and change on two adjacent watersheds in the Coastal Plain of the CBW, using Soil and Water Assessment Tool (SWAT) model. We prepared six climate sensitive scenarios to assess the individual effects of variations in CO2 concentration (590 and 850 ppm), precipitation increase (11 and 21 %) and temperature increase (2.9 and 5.0 °C), and considered the predicted climate change scenario using five general circulation models (GCMs) under the Special Report on Emissions Scenarios (SRES) A2 scenario. Using SWAT model simulations from 2001 to 2014, as a baseline scenario, the predicted water and nitrate budgets under climate variability and change scenarios were analyzed at multiple temporal scales. Compared to the baseline scenario, precipitation increase of 21 % and elevated CO2 concentration of 850 ppm significantly increased stream flow and nitrate loads by 50 % and 52 %, respectively, while, temperature increase of 5.0 °C reduced stream flow and nitrate loads by 12 % and 13 %, respectively. Under the climate change scenario, annual stream flow and nitrate loads showed an average increase of nearly 40 %, relative to the baseline scenario. Differences in hydrological responses observed from the two watersheds were primarily attributed to contrasting land use and soil characteristics. The watershed with larger percent croplands indicated increased nitrate yield of 0.52 kg N ha−1 compared to the one with less percent croplands under the climate change scenario, due to increased export of nitrate derived from fertilizer. The watershed dominated by poorly-drained soils showed a lower increase in nitrate yield than one dominated by well-drained soils, due to a high potential of nitrate loss in surface runoff and enhanced denitrification. To mitigate increased nitrate loads potentially caused by climate change, the enhanced implementation of conservation practices would be necessary for this region in the future. These findings assist watershed managers and regulators as they seek to establish effective adaptation strategies to mitigate water quality degradation in this region.


2021 ◽  
Author(s):  
Geet K Grewal

Climate change is expected to lengthen the growing season for plants in many temperate regions. The purpose of this study is to develop future growth estimates for trees in Earlscourt Park, Toronto. The i-Tree Forecast model, in combination with climate change scenarios provided by the Canadian Climate Change Scenario Network, were used to build trajectories of future tree growth and mortality. Tree growth forecasts were greatest for the climate change scenario with the longest growing season length. Results highlight future vulnerability in two tree species common to the park, honey locust and Norway maple. A comparison of the leaf area estimates produced by i-Tree Streets and i-Tree Eco was also conducted. These models showed differences in their prediction of leaf area, a key metric for ecological service provision. Forecasting tree growth and mortality in urban parks can inform management plans that seek to maximize the flow of future ecological benefits.


2015 ◽  
Vol 24 (12) ◽  
pp. 1649-1656 ◽  
Author(s):  
Jun-Ho Lee ◽  
Sung-Kee Yang ◽  
Min-Chul Kim

2022 ◽  
Author(s):  
Gilmar Veriato Fluzer Santos ◽  
Lucas Gamalel Cordeiro ◽  
Claudio Antonio Rojo ◽  
Edison Luiz Leismann

Abstract Global warming has divided the scientific community worldwide with predominance for anthropogenic alarmism. This article aims to project a climate change scenario using a stochastic model of paleotemperature time series and compare it with the dominant thesis. The ARIMA model – an integrated autoregressive process of moving averages, known as Box-Jenkins - was used for this purpose. The results showed that the estimates of the model parameters were below 1°C for a scenario of 100 years which suggests a period of temperature reduction and a probable cooling, contrary to the prediction of the IPCC and the anthropogenic current of an increase in 1.50° C to 2.0° C by the end of this century. Thus, we hope with this study to contribute to the discussion by adding a statistical element of paleoclimate in counterpoint to the current consensus and to placing the debate in a long-term historical dimension, in line with other research present in climate sciences and statistics.


2012 ◽  
Vol 1 (33) ◽  
pp. 23
Author(s):  
Toon Verwaest ◽  
Sebastian Dan ◽  
Johan Reyns ◽  
Ellen Meire ◽  
Tina Mertens ◽  
...  

A master plan to strengthen the weak links in the coastal defence line in the Belgium is established based on coastal flooding risk calculations. This plan takes into account an average climate change scenario to be expected in the coming decades until 2050, namely an increase of surge levels of 30 cm. More long term climate change scenarios were also investigated. A worst credible extreme scenario for the 21st century change of the hydrometeorological North Sea climate was defined, with a mean sea level rise of 2 m combined with a 8% increase of extreme wind speeds. Alternative measures to manage coastal flooding risks under such climate scenario were studied to find robust measures to adapt coastal protection to climate change until 2100. The Belgian coastal zone is low-lying, highly populated and it is very vulnerable to increased coastal flooding risks by climate change. The methodology for the coastal flooding risk calculations is based on a chain of numerical models describing characteristics of storm surges with different return periods approaching the coastal defences, the failure behaviour of these defences, the hydraulics of flooding in case of failure by breaching, overflow or overtopping of the defences and finally a GIS-based damage and casualties module adopted for use within Flanders region based on available detailed GIS-data on people and assets. The rate of increase of coastal flooding risks for different climate change scenarios is quantified using a simplified version of the chain of models described above. This generalised model chain was validated by comparing with the results of the detailed model chain for the anno 2000 case. However, flooding paths via the coastal harbours as well as local risks on top of the sea dikes in the coastal towns were disregarded in the simplified model. As a consequence the results on climate change sensitivity are limited in scope to the risks associated with breaching of the sea dikes and dunes. The calculation results show a dramatic increase of the coastal flooding risks due to breaches during 21st century. For an average climate change scenario, with an increase of surge levels by 0.8 m, the risks increase by a factor 10. For the worst credible climate change scenario, with an increase of surge levels by 2.4 m, the risks increase by a factor 100. Existing coastal defences in the Belgian coastal zone are relatively low-crested compared with surge levels. This fact increases the vulnerability of this coastal zone to climate change, as was shown by the coastal flood risk calculation results. Different adaptation measures to manage these increasing risks were compared. Based on their effectiveness to reduce risks as well as estimates of costs for implementation it was concluded that efficient adaptation measures consist of heightening and/or widening the existing dunes, sea dikes and beaches. Future research will investigate which adaptation measures can be developed in the coastal harbours for maintaining safety against flooding under climate change.


Sign in / Sign up

Export Citation Format

Share Document