Streamflow prediction using machine learning approaches with different shared socioeconomic pathways (SSPs)

Climate change, particularly extreme weather events, has significantly affected various sectors, including agriculture, human health, water resources, sea levels, and ecosystems. It is anticipated that the intensity, duration, and frequency of these extremes will escalate in the future. This study aims to discover the association between temperature extremes and agricultural yield and to project these extremes using machine learning (ML) and deep learning (DL) models with CMIP6 (Coupled Model Intercomparison Project Phase 6) data under two SSPs (Shared Socioeconomic Pathways). A bi-wavelet coherence technique is employed to investigate the association, providing detailed information in both the frequency and time domains for the period of 1980–2014. Various ML and DL models are trained and tested for the periods of 1985–2004 and 2005–2014, respectively, with gradient boosting machine chosen for projecting temperature extremes based on its superior performance. Mann-Kendall test is used for trend analysis in the projected temperature extremes. The results indicate strong negative and positive associations between TN10p (Cold nights) and TN90p (Warm nights), respectively, with wheat production. Additionally, there is a long-term negative association of CSDI (Cold Spell Duration Indicator) and strong positive association of WSDI (Warm Spell Duration Indicator) with rice yield. Projected results show an increase and decrease under SSP2-4.5 and SSP5-8.5, respectively, in DTR (Diurnal Temperature Range) at most stations. TN10p will increase in the future at most stations, with exceptions such as Muree station where it decreases during 2025–2049 and then increases under both SSPs. Projections show that TXn (annual or monthly minimum value of daily maximum temp) will increase in the future, with Muree station exhibiting the lowest value close to zero, while the average maximum value is around 20 °C at Khanpur station. Trend analysis reveals significantly increasing trend in TR20 (Tropical nights) and decreasing trend in CSDI in future durations under both SSPs. These findings hold implications for policymakers and stakeholders in various departments, including agriculture, health, and water resources management.

In this study, a machine learning model was used to investigate the potential consequences of climate change on vegetation growth. The methodology involved analyzing the historical Normalized Difference Vegetation Index (NDVI) data and future climate projections under four Shared Socioeconomic Pathways (SSPs). Data from the Global Inventory Monitoring and Modeling System (GIMMS) dataset for the period 1981–2000 were used to train the machine learning model, while CMIP6 (Coupled Model Intercomparison Project Phase 6) global climate projections from 2021–2100 were employed to predict future NDVI values under different SSPs. The study results revealed that the global mean NDVI is projected to experience a significant increase from the period 1981–2000 to the period 2021–2040. Following this, the mean NDVI slightly increases under SSP126 and SSP245 while decreasing substantially under SSP370 and SSP585. In the near-term span of 2021–2040, the average NDVI value of SSP585 slightly exceeds that of SSP245 and SSP370, suggesting a positive vegetation development in response to a more pronounced temperature increase in the near term. However, if the trajectory of SSP585 persists, the mean NDVI will commence a decline over the subsequent three periods (2041–2060, 2061–2080, and 2080–2100) with a faster speed than that of SSP370. This decline is attributed to the adverse effects of a rapid temperature rise on vegetation. Based on the examination of individual continents, it is projected that the NDVI values in Africa, South America, and Oceania will decline over time, except under the scenario SSP126 during 2081–2100. On the other hand, the NDVI values in North America and Europe are anticipated to increase, with the exception of the scenario SSP585 during 2081–2100. Additionally, Asia is expected to follow an increasing trend, except under the scenario SSP126 during 2081–2100. In the larger scope, our research findings carry substantial implications for biodiversity preservation, greenhouse gas emission reduction, and efficient environmental management. The utilization of machine learning technology holds the potential to accurately predict future changes in vegetation growth and pinpoint areas where intervention is imperative.

Crop rotation has been widely used to enhance crop yields and mitigate adverse climate impacts. The existing research predominantly focuses on the impacts of crop rotation under growing season (GS) climates, neglecting the influences of non-GS (NGS) climates on agroecosystems. This oversight limits our understanding of the comprehensive climatic impacts on crop rotation and, consequently, our ability to devise effective adaptation strategies in response to climate warming. In this study, we examine the impacts of both GS and NGS climate conditions on the yield effect of the preceding crop in corn-soybean rotation systems from 1999 to 2018 in the US Midwest. Using causal forest analysis, we estimate that crop rotation increases corn and soybean yields by 0.96 and 0.22 t/ha on average, respectively. We then employ statistical models to indicate that increasing temperatures and rainfall in the NGS reduce corn rotation benefits, while warming GS enhances rotation benefits for soybeans. By 2051-2070, we project that warming climates will reduce corn rotation benefits by 6.74% under Shared Socioeconomic Pathway (SSP) 1-2.6 and 17.18% under SSP 5-8.5. For soybeans, warming climates are expected to increase rotation benefits by 8.36% under SSP 1-2.6 and 13.83% under SSP 5-8.5. Despite these diverse climate impacts on both crops, increasing crop rotation could still improve county-average yields, as neither corn nor soybean was fully rotated. If we project that all continuous corn and continuous soybeans are rotated by 2051-2070, county-average corn yields will increase by 0.265 t/ha under SSP 1-2.6 and 0.164 t/ha under SSP 5-8.5, while county-average soybean yields will gain 0.064 t/ha under SSP 1-2.6 and 0.076 t/ha under SSP 5-8.5. These findings highlight the effectiveness of crop rotation in the face of warming NGS and GS in the future and can help evaluate opportunities for adaptation.

Effect difference of climate change and urbanization on extreme precipitation over the Guangdong-Hong Kong-Macao Greater Bay Area

The global water cycle has undergone considerable changes since pre-industrial times due to global climate change and land-use changes. These drivers will almost certainly continue to change during the course of this century. However, where, how, and to which extent terrestrial moisture recycling will change as a result remains unclear.Mutually consistent scenarios of climate change and land-use changes for the 21st century are provided by the Shared Socioeconomic Pathways (SSPs). The SSPs provide a framework of five different narratives involving varying degrees of challenges associated with mitigation or adaptation. From each narrative follow different implications for emissions, energy, and land use. The SSPs serve as the conceptual framework behind the sixth generation of the Coupled Model Intercomparison Project, CMIP6.Terrestrial moisture recycling is often assessed using atmospheric moisture tracking models. An example is UTrack, a Lagrangian model to track moisture through three-dimensional space. Here we present a new forward-tracking version of UTrack that is forced by output of a CMIP6 model to study how terrestrial moisture recycling may change across the globe until the end of the  21st century in a range of SSPs, from mild to severe: SSP1-2.6, SSP2-4.5, SSP3-7.0, and SSP5-8.5. For this forcing, we chose the Norwegian Earth System Model version 2, or NorESM2. It has a temporal resolution of one day and a spatial resolution of 1.25° × 0.9375° at eight pressure levels.We find that across the 21st century, the global terrestrial moisture recycling ratio decreases with the severity of the Shared Socioeconomic Pathways (SSPs). We calculate a decrease in global terrestrial precipitation recycling by 2.1% with every degree of global warming. Because the SSPs represent internally consistent scenarios of both global warming and global land cover changes, it is hard to distinguish the relative contributions of these two, but the evidence points at a major influence of global warming on moisture recycling.We find spatial differences in trends in recycling ratios, but which are broadly consistent among SSPs. If a change in precipitation (either drying or wetting) coincides with an increase in terrestrial precipitation recycling ratio, we call it land-dominated. We call the change in precipitation ocean-dominated if it coincides with a decrease in terrestrial precipitation recycling ratio. Land dominance tends to occur in regions with already large terrestrial precipitation recycling ratios, mainly interior South America (land-dominated drying) and eastern Asia (land-dominated wetting). Land-dominated drying may also happen in eastern Europe, in central America and in subtropical sub-Saharan Africa. Ocean-dominance, mainly in the form of wetting, is found primarily in the high northern latitudes and in central Africa.We also simulated the changes in basin recycling for the 27 major river basins of the world, confirming the overall tendency of decreasing recycling with severity of the SSP, as well as its spatial variations.

Studying the evolutions, differences, and water security impacts of water demands under shared socioeconomic pathways: A SEMs-bootstrap-ANN approach applied to Sichuan Province

This study aims to investigate the historical (1951–2024) and future projected (2026–2099) climate trends and change points in the Vellar River Basin under Shared Socioeconomic Pathways (SSP) using time series observations and downscaled Global Climate Model (GCM). Trends of rainfall and temperature were assessed based on the Mann–Kendall test. The change points detection were carried using Pettitt’s test, Standard Normal Homogeneity test, Buishand's range test and Von Neuman ratio test. The results revealed that historical rainfall found a declining trend seasonally as well as annually, with significant change points at 1979, 1981, and 1988. Future projections showed decreasing trend in rainfall, with notable change points at 2058, 2067, and 2084. The station Virudhachalam during Kharif, Vazhapadi and Karumandurai during Rabi and Annual period recorded more significant decreasing trend. The result of historical and future temperature projection displayed a significant upward trend. The historical minimum and maximum temperatures increased from 0.44 °C to 0.88 °C and 1.11 °C to 1.7 °C, respectively with change points for minimum temperature at 1996 and maximum temperature at 1979. The future predicts of temperature recorded an increasing trend of 1.5 °C, 2.0 °C, and 3.0 °C for maximum temperatures and 0.9 °C, 1.2 °C, and 1.5 °C for minimum temperatures under SSP 2.6, SSP 4.5, and SSP 8.5 scenario, respectively. Change points in maximum temperature are expected in the 2050s and 2060 for SSP 2.6 and SSP 4.5. Whereas SSP 8.5 anticipates at later 2080s, indicating a two-stage warming pattern with an early gradual increase followed by rapid rise towards the end of the century. These findings concluded by recommending the policy makers to develop climate adaptation strategies for agricultural and water management to mitigate the potential impacts of future climate condition.

A series of global actions have been made to address climate change. As a recent developed climate policy, Intended Nationally Determined Contributions (INDC) have renewed attention to the importance of exploring temperature rise levels lower than 2 °C, in particular a long-term limit of 1.5 °C, compared to the preindustrial level. Nonetheless, achieving the 2 °C target under the current INDCs depends on dynamic socioeconomic development pathways. Therefore, this study conducts an integrated assessment of INDCs by taking into account different Shared Socioeconomic Pathways (SSPs). To that end, the CEEP-BIT research community develops the China’s Climate Change Integrated Assessment Model (C3IAM) to assess the climate change under SSPs in the context of with and without INDCs. Three SSPs, including “a green growth strategy” (SSP1), “a more middle-of-the-road development pattern” (SSP2) and “further fragmentation between regions” (SSP3) form the focus of this study. Results show that after considering INDCs, mitigation costs become very low and they have no evident positive changes in three SSPs. In 2100, a temperature rise would occur in SSP1-3, which is 3.20, 3.48 and 3.59 °C, respectively. There are long-term difficulties to keep warming well below 2 °C and pursue efforts toward 1.5 °C target even under INDCs. A drastic reduction in greenhouse gas emissions is needed in order to mitigate potentially catastrophic climate change impacts. This work contributes on realizing the hard link between the earth and socioeconomic systems, as well as extending the economic models by coupling the global CGE model with the economic optimum growth model. In C3IAM, China’s energy consumption and emissions pattern are investigated and refined. This study can provide policy makers and the public a better understanding about pathways through which different scenarios could unfold toward 2100, highlights the real mitigation and adaption challenges faced by climate change and can lead to formulating effective policies.

<p>Agricultural sector, being the largest consumer of water is greatly affected by climatic variability and disasters. Most parts of the world already face an enormous challenge in meeting competitive and conflicting multi-sector water demands. Climate change has further exacerbated this challenge by putting the sustainability of current cropping patterns and irrigation practices in question. For ensuring climate-resilient food production, it is crucial to examine the patterns of the projected climate and potential impacts on the agricultural sector at a basin scale. Hence, this study was carried out for an already water-scarce basin, Rushikulya River basin (RRB), located in the coastal region of eastern India. The bias-corrected NorESM2-MM general circulation model of Coupled Model Intercomparison Project-6 (CMIP6) was used in this study under four shared socioeconomic pathway (SSPs) scenarios, namely SSP126, SSP245, SSP370 and SSP585. The projected climatic parameters and crop water demands of the basin were analyzed assuming existing cropping pattern in the future. Analysis of the results reveals a significant and rapid increase in the temperature at a rate of 0.02-0.5ºC/year during 2026-2100 under all SSPs except SSP126, whereas the rainfall is expected to increase slightly during 2026-2100 as compared to the baseline period (1990-2016), especially in the far future (2076-2100) under all the SSPs. In contrast, monsoon rainfall is predicted to decrease under SSP245 and SSP370, while a slight increase in the monsoon rainfall is evident under SSP126 and SSP585. Although the rainy days will decrease slightly in the future 25-year time window, the number of heavy rainfall events is predicted to increase by two to three times. Also, retrospective analysis of rainfall and evapotranspiration suggested an existence of rainfall deficit (rainfall-evapotranspiration) in the basin throughout the year, except during July to September. The rainfall deficit in the basin during 2026-2100 is found to remain more or less same in the non-monsoon season, except for the month of October under SSP245, SSP370 and SSP585 scenarios where deficit increases by two folds. Rainfall is expected to be in surplus by 4 to 5 times higher under all SSPs except for SSP245. As to the evapotranspiration, an insignificant increasing trend is observed under future climatic condition with only 2 to 4% rise in the crop water demand compared to the baseline period. As the basin is already water stressed during most months in a year under baseline and future climatic conditions, continuing the current practice of monsoon paddy dominant cultivation in the basin will further aggravate this situation. The results of this study will be helpful in formulating sustainable irrigation plans and adaptation measures to address climate-induced water stress in the basin.</p><p><strong>Keywords:</strong> Climate change; CMIP6; SSP; Monsoon rainfall; Temperature; Crop water demand.</p>

Optimized machine learning approaches for identifying vertical temperature gradient on ballastless track in natural environments

Global urbanization projections for the Shared Socioeconomic Pathways

The Nature Futures Framework (NFF) was developed for the Intergovernmental Science-Policy Platform on Biodiversity and Ecosystem Services (IPBES) to explore scenarios that represent a diversity of positive relationships between humans and nature. Widely used in global environmental assessments, the shared socio-economic pathways (SSPs) in combination with the representative concentration pathways (RCPs) were developed for climate change assessments. However, the relationship at a global level between the SSP–RCP scenario outcomes and the framing of the NFF around three value perspectives—Nature for Nature, Nature for Society, and Nature as Culture—has not been established. Here, we demonstrate a method to map onto the NFF value perspectives results from alternative SSP scenarios, each paired with an RCP consistent with the SSP storyline. For each of the NFF value perspectives, multiple elements were identified, each represented by one or more nature-focused indicators. Values for these indicators, for the different SSP scenario outcomes, were derived from an existing application of a global land system model, LandSyMM. A score for each indicator is estimated by comparing the indicator values against a normative target range. We find that only SSP1 provides greater benefits for Nature as Culture and Nature for Society relative to a 2010 baseline. Overall, the SSP scenarios provide fewer benefits for Nature for Nature, consistent with a bias towards the provision of material over non-material ecosystem services. The results demonstrate that the SSP–RCP scenario framing captures some, but not all, of the dimensions of nature and that alternative scenario framings, such as the NFF, are needed to study a broader range of biodiversity and ecosystem related questions as well as exploring positive futures.

Climate change will create numerous risks for human health, including impacts associated with temperature extremes, diarrheal diseases, and undernutrition. Such risks, along with other socioeconomic and development trends, will affect cause-of-death patterns experienced in the coming decades. This study explores future mortality trends using the shared socioeconomic pathways (SSP) framework, a widely utilized tool for understanding socioeconomic development trends in a world with climate change. Existing projections for GDP, urbanization, and demographic trends based on SSP narratives are incorporated into an integrated assessment model, International Futures (IFs), in order to project mortality levels by cause of death for all countries from 2020 to 2100. Under more optimistic SSPs, non-communicable diseases (NCDs) rise as a proportion of all deaths, particularly in low- and middle-income countries, while more pessimistic SSPs suggest a continued high burden of largely preventable communicable diseases. In high-income countries, significant continued burdens of NCDs are projected for the remainder of the century under all SSPs. Comparisons are also made to recent cause-of-death projections from the Institute for Health Metrics and Evaluation (IHME) to assess how the IFs and IHME models vary.Electronic supplementary materialThe online version of this article (10.1007/s10584-020-02824-0) contains supplementary material, which is available to authorized users.

Transboundary Nile basin dynamics: Land use change, drivers, and hydrological impacts under socioeconomic pathways

Performance optimization of wireless networks is typically complicated because of high computational complexity and dynamic channel conditions. Considering a specific case, the recent introduction of intelligent reflecting surface (IRS) can reshape the wireless channels by controlling the scattering elements' phase shifts, namely, passive beamforming. However, due to the large size of scattering elements, the IRS's beamforming optimization becomes intractable. In this article, we focus on machine learning (ML) approaches for complex optimization problems in wireless networks. ML approaches can provide flexibility and robustness against uncertain and dynamic systems. However, practical challenges still remain due to slow convergence in offline training or online learning. This motivated us to design a novel optimization-driven ML framework that exploits the efficiency of model-based optimization and the robustness of model-free ML approaches. Splitting the control variables into two parts allows one part to be updated by the outer loop ML approach while the other part is solved by the inner loop optimization. The case study in IRS-assisted wireless networks confirms that the optimization-driven ML framework can improve learning efficiency and the reward performance significantly compared to conventional model-free ML approaches.