Humans benefit from a multitude of resources and processes supplied by natural ecosystems . These benefits (collectively known as ecosystem services) include water resources suitable for supporting various sectors of society, such as agriculture, construction, daily living, energy, fishing, forestry, manufacturing, public health, recreation, and transportation. Climate change is frequently cited as one possible external driver of ecosystem services . Because climate is temporally and spatially dependent, change at a global scale differs from regional or local scales. Some considerations when discussing temporal climate change include amplitude, duration, and gradient .
In many studies, the duration of climate change is considered short-term (years to decades) and long-term (hundreds to thousands of years) variability . Short-term climate variability is attributed to oscillations in the sea surface temperature (SST) that alter ocean currents and overlying air pressure resulting in a redistribution of temperature and precipitation . Long-term climate variability is attributed to alterations in external processes leading to a redistribution of heat at depth in the world's oceans . Some possible long-term processes  are (1) the changing solar radiation due to sunspot activity, (2) the addition of carbon dioxide from volcanic activity, and (3) the reversal of the earth's magnetic field.
The El Niño Southern Oscillation (ENSO) is considered the strongest short-term periodic fluctuation (2-7 years) with a rise (El Niño) or decrease (La Niña) of SST in the equatorial Pacific Ocean . This teleconnection is not globally uniform in the U.S., and drought conditions induced by an El Niño event commonly affect the northern latitudes, and a La Niña event affects the southern latitudes . Droughts have tremendous consequences on the physical, economic, social, and political elements of our environment . They affect surface and groundwater resources by diminishing the water supply, water quality, riparian habitat, power generation, and range productivity. Other consequences often include crop failure, debris flows, insect infestations, pestilence, violent conflict, wildfires, and disruptions to economic and social activities .
Should natural or anthropogenic forcing influence the frequency or intensity of climate change, there is an increased likelihood for drought hazards placing national and global security at risk . For this reason, accurate and timely climate-change information and related predictions could benefit many sectors of society, but the scale-dependent complexities render it a challenge to model. Specifically, climate forcing is known to interact with ecosystems which is characterized by coupled, nonlinear, and multivariate processes. Data associated with these systems are typically sparsely populated ranging spatially from local (1,000s km2) to global and temporally from immediate (1-10s years) to long-term (100s to 1,000s years). This makes the construction of process-based models difficult. One critical issue is the lack of essential calibration data which results in large inaccuracies . Also, process-based modeling schemes are commonly too rigid with respect to detecting unexpected features like the onset of trends, non-linear relations, or patterns restricted to sub-samples of a data set. These shortcomings created the need for an alternate modeling approach capable of using available data. This paper demonstrates the efficacy of using data mining to understand the effects of climate change on water-resource dependent ecosystem services. The objectives are: (1) hindcasting 2,000 years of temperature and precipitation across states in the south-central and southwest U.S.; (2) forecasting climate-induced groundwater recharge variability across subbasins in mid-western U.S.; and (3) forecasting climate-change effects on post-fire hydrology and geomorphology in the western U.S.
Was this article helpful?