11 |
Methodology to Predict Daily Groundwater Levels by the Implementation of Machine Learning and Crop ModelsGutierrez, Sandra Milena Guzman 12 August 2016 (has links)
The continuous decline of groundwater levels caused by variations in climatic conditions and crop water demands is an increased concern for the agricultural community. It is necessary to understand the factors that control these changes in groundwater levels so that we can better address declines and develop improved conservation practices that will lead to a more sustainable use of water. In this study, two machine learning techniques namely support vector regression (SVR) and the nonlinear autoregressive with exogenous inputs (NARX) neural network were implemented to predict daily groundwater levels in a well located in the Mississippi Delta Region (MDR). Results of the NARX model indicate that a Bayesian regularization algorithm with two hidden nodes and 100 time delays was the best architecture to forecast groundwater levels. In another study, the SVR and the NARX model were compared for the prediction of groundwater withdrawal and recharge periods separately. Results from this study showed that input data classified by seasons lead to incremental improvements in the model accuracy, and that the SVR was the most efficient machine learning model with a Mean Squared Error (MSE) of 0.00123 m for the withdrawal season. Analysis of input variables such as previous daily groundwater levels (Gw), precipitation (Pr), and evapotranspiration (ET) showed that the combination of Gw+Pr provides the optimal set for groundwater prediction and that ET degraded the modeling performance, especially during recharge seasons. Finally, the CROPGRO-Soybean crop model was used to simulate the impacts of different volumes of irrigation on the crop height and yield, and to generate the daily irrigation requirements for soybean crops in the MDR. Four irrigation threshold scenarios (20%, 40%, 50% and 60%) were obtained from the CROGRO-Soybean model and used as inputs in the SVR to evaluate the predicted response of daily groundwater levels to different irrigation demands. This study demonstrated that conservative irrigation management, by selecting a low irrigation threshold, can provide good yields comparable to what is produced by a high volume irrigation management practice. Thus, lower irrigation volumes can have a big impact on decreasing the amount of groundwater withdrawals, while still maintaining comparable yields.
|
12 |
Investigating Late Woodland-Period Aquatic Catchments through Freshwater Mussel Assemblage CompositionGilleland, Sarah K 12 August 2016 (has links)
During the Late Woodland Period in the American Southeast, the amount of space that any individual group could exploit began to shrink, due to the presence of other groups on the landscape. Resource expansion occurred to augment food supplies, resulting in increased exploitation of mussel beds. Because mussels can be extremely sensitive to the characteristics of the waterways they live in, the specific habitat requirements of these animals can be used to reconstruct the environments they were recovered from. In this thesis I use freshwater mussel assemblages to reconstruct hypothetical aquatic catchments and map them onto modern rivers in the Yazoo River Basin and the Tombigbee River Basin. These are used to test ethnographic models of exploited space. I also use detrended correspondence analysis to test if sites exist in mathematical space like they do in physical space along the Yazoo River basin, as observed in the Tombigbee River basin.
|
13 |
A Wind Resource Assessment of the Mississippi DeltaDealy, Jessica 11 May 2013 (has links)
The hypothesis tested was that a site in Leflore County, Mississippi, located on the bluff above the Mississippi River flood plain (the Delta) would experience wind speeds adequate for power generation. Wind measurements were collected at a height of 55 m (above ground level) between October 2011 and October 2012. Winds at this height were predominately southeasterly with a mean wind speed less than 4 m/s. Winds did not accelerate above this bluff. Low surface friction of the Delta was not beneficial due to the predominant wind direction. To better understand Delta wind patterns, an S-mode varimax-rotated principal component analysis (RPCA) was performed on monthly 30 m North American Regional Reanalysis (NARR) wind data. Three areas for future wind resource assessment measurements were determined. Each pattern highlighted more energetic wind speeds areas, none of which included the measurement site. The RPCA method was successful in delineating homogeneous wind speed patterns.
|
14 |
Intestinal digenetic trematodes found in double-crested cormorant populations in the Mississippi Delta and the potential impact of these parasites on commercial and wild fish species found in this regionO'Hear, Mary McPherson 06 August 2011 (has links)
Double-crested cormorants have steadily increased in the Mississippi Delta. This bird serves as a definitive host for digenetic trematodes, many of which infect fish. To identify these digeneans in cormorants and determine the impact these infections have on wild fish in the Mississippi Delta, two surveys were done. Cormorants were collected for two years in the Mississippi Delta. At necropsy trematodes were collected and identified morphologically and molecularly as: Austrodiplostomum ostrowskiae, Hysteromorpha triloba, Drepanocephalus spathans, Ascocotyle longa and Pseudopsilostoma varium. Additionally, 14 fish species were collected from a Mississippi Delta lake. Fish were examined for parasites and Posthodiplostomum minimum metacercariae were found in multiple organs in 6/14 fish species. The 18S gene sequences of these metacercariae were identical to published P. minimum sequences, whereas the cytochrome oxidase I (COI) sequences matched published COI sequences for Posthodiplostomum sp. 3, 5 and 8, suggesting subspecies of Posthodiplostomum in this fish population.
|
15 |
Consumption of fruits and vegetables in the Mississippi Delta and the role of the food environmentGiscombe, Shannon 09 August 2022 (has links)
Differences in the prevalence of obesity are generally associated with disparities in the food environment which partially determine diet quality. In this research, I examine the relationship between the local food environment and the consumption of fruit and vegetables among individuals living in the Mississippi Delta region using survey and store availability data for individuals living in seven counties with the highest obesity rates in the state. An ordered probit model with an endogenous covariate is used to assess the marginal effect of food environment variables on the frequency of fruit or vegetable consumption. I find that longer distance traveled to the nearest full-service grocery store is associated with lower frequency of vegetable consumption, while access to public transportation is generally associated with a higher frequency of consumption. Insights from this study could prove helpful for health officials and policymakers tasked with designing and implementing localized interventions that improve the food environment and increase healthy food access.
|
16 |
Uncertainty analysis for runoff, crop yield, sediment, and nutrient loads in the Mississippi Delta region using APEXMéndez Monroy, Javier Fernando 10 May 2024 (has links) (PDF)
Understanding the dynamics of agricultural basins has been difficult for decision-makers when developing cost-effective plans. An uncertainty analysis evaluates the impact of information gaps on hydrologic model’s output and performance. The Agricultural Policy/Environmental Extender (APEX v1501) was used to predict runoff, crop yield, sediment load, total phosphorus, and total nitrogen from agricultural fields in the Mississippi Delta to investigate the impact of using different input variables (climate, soils, and management practices) on mechanistic models. Results indicated that the use of surrogate information such as weather data from close weather stations, a predominant soil series, and simulated irrigation schedules, could be considered when available in situ information is restricted. Overall results provided information on model setup and output interpretation that may be useful to Mississippi Delta decision-makers.
|
17 |
Where’s the food? Food insecurity and Black food geographies in the Mississippi DeltaPatterson, Taylor 10 May 2024 (has links) (PDF)
This thesis examines the historical and contemporary roots of food apartheid in the Yazoo-Mississippi Delta, while employing a Black Food Geographies approach to highlight and interpret the lived experiences of people in the Delta. This work draws on interviews and participant observation in Clarksdale, Mississippi, to decenter popular narratives around food insecurity and region and instead center the ideas and opinions of people directly impacted. The thesis highlights Black Deltans’ experiences and understandings of food and foodways to provide a nuanced picture of how residents interpret, negotiate, and challenge the region’s unequal food geographies in light of a longer history of food apartheid
|
18 |
Optimizing water, nitrogen, and row patterns for irrigated corn and soybean in the Mississippi DeltaVargas Loyo, Amilcar Jose 10 May 2024 (has links) (PDF)
Integrating water-saving technologies with optimized nutrient management strategies provides opportunities for sustainable agriculture in the Mississippi Delta. Three studies were conducted to determine the effects of irrigation systems, row patterns, and nutrient management strategies on corn and soybeans. The first study determined the effects of irrigation, row pattern, and nitrogen (N) placement methods on corn (Zea mays L.) productivity and N use efficiency. The effects of N placement methods were only evident in 2021 when the rainfall events were more pronounced than in 2020. Regardless of the row pattern, placing N with one knife increased corn grain yield and the agronomic N use efficiency by 14.1% and 16.8%, respectively, when compared to the surface dribble method. The second study investigated the effects of irrigation systems and row patterns on grain yield, grain quality parameters, and irrigation water use efficiency (IWUE) on soybeans (Glycine max L.) grown on Sharkey clay. When irrigation was triggered at -80 kPa, furrow-irrigated soybeans produced 3.9% more grain yield compared to sprinkler-irrigated soybeans. The total amount of water applied by the sprinkler irrigation system represented 19-52% of the total amount applied by the furrow system. Narrow-row patterns achieved greater IWUE than single-row patterns. In the third study, we evaluated the effects of N and irrigation levels on grain quantity, quality, and plant growth on corn grown across different soil electrical conductivity (EC) levels and its implications for variable rate technology. Corn grain yields increased with the increase of N and irrigation levels but decreased as soil EC decreased. Overall, maintaining a sprinkler irrigation threshold between -40 and -70 kPa optimized corn yield. In addition, these results did not provide enough evidence to use variable rate irrigation or variable rate N application in the Mississippi Delta.
|
19 |
Exploring the late Holocene sedimentary record of the Mississippi Delta for climate/sea level connectionsJanuary 2008 (has links)
The main outcome of this dissertation is a highly detailed RSL record constructed for the time interval 600 to 1600 AD to explore the eustatic response of sea level to the atmospheric warming that occurred during the Medieval Warm Period (∼900 to ∼1200 AD) and the transition into the Little Ice Age (∼1400 to ∼1900 AD). This new record was obtained in the microtidal Mississippi Delta and contains 28 sea-level index points that track ∼60 cm of relative sea-level rise. Basal peat was used as a tracer of sea-level, and age control was obtained by AMS 14C dating. All data were plotted as error boxes using 2 sigma confidence levels. A clustering of index points between 1000 and 1200 AD suggests an increase in the rate of sea-level rise. While this suggests a fluctuating eustatic sea level, any centennial-scale fluctuation could not have had an amplitude larger than ~30 cm. Rates of sea-level change calculated from the first derivative of a third-order polynomial function fitted through the central point of each error box (r2=0.96) indicate that the maximum rate of sea-level rise occurred around 1100 AD, which slightly postdates peak Medieval warmth according to most Northern Hemisphere paleotemperature records. The dominant control of the long-term rate (0.56 mm yr-1) of RSL rise obtained from the new reconstruction is glacial isostasy in the form of forebulge collapse. Subtracting the rate of eustatic sea level rise for the 20th century (1.7 mm yr-1) (Church and White, 2006) from the rate of sea level rise captured by the Pensacola (Florida) tide gauge (2.2 mm yr-1), an area that is considered tectonically stable, yields a residual of 0.5 mm yr-1. This figure is in agreement with the long-term rate obtained in this study. This value is also very close to what some geophysical models predict as the present-day rate of glacial isostatic adjustment for the north central Gulf Coast. Taking the ratio of the instrumental rate for the last 90 years captured by the Pensacola tide gauge (2.2 mm yr-1) to the long-term geologic rate (0.56 mm yr-1) indicates a four-fold increase in the rate of relative sea level rise during the 20th century compared to that of the previous millennium. Given that at time scales of one-thousand years processes like glacial isostasy and tectonic subsidence behave essentially linearly, and that both records are free of compaction, the increase can only result from an acceleration in the rate of global sea level rise. / acase@tulane.edu
|
20 |
EFFECTS OF FAMILY STRUCTURE ON EDUCATIONAL ATTAINMENT AND HEALTH INSURANCE COVERAGE OF YOUTH IN THE LOWER MISSISSIPPI DELTA REGIONSmith, Chaquenta L 01 January 2013 (has links)
A large body of research, typically nationally focused, has examined the relationship between family structure, educational attainment, and healthcare access. Within this field of study, there is limited availability of regionally based studies, specifically the Lower Mississippi Delta (LMD) region. This exploratory study examines the effects of family structure on high school graduation rates and health insurance coverage within the LMD region. The objective is to determine if family structure has a direct impact on the educational attainment and health outcomes of a child within the region using concepts from nationally focused literature. Through the use of an OLS regression, we find that family structure does not have a strong impact on the educational attainment of children within the region. However, we did find that family structure had a strong impact on the health insurance coverage of youth within the region. Additionally, we examine the impact that spatial location and race has on these variables. These results can encourage the development of potential intervention programs, outreach initiatives, and other programs geared toward helping youth within the region. The study's conclusions provide insight on the impact of family structure on health and education thus encouraging further research within the LDM region.
|
Page generated in 0.0692 seconds