WELCOME
Welcome to our site. Our aim is to investigate the impact of sedimentation on river deltas and to inform people about it.
What Do We Want to Do?
We study sediment formation in the Mississippi River Delta. Sediment formation causes the river delta to shrink. This negatively affects the economic activities of the people living there. Our aim is to warn the public by using the data we receive from NASA and to minimize the damage to the public.
Sedimentation Formation
Sedimentation is the deposition of sediments. It takes place when particles in suspension settle out of the fluid in which they are entrained and come to rest against a barrier. This is due to their motion through the fluid in response to the forces acting on them: these forces can be due to gravity, centrifugal acceleration, or electromagnetism.
Most of the sedimentary rocks are formed as a result of the accumulation of elements of various sizes, which are formed by the erosion of the earth by external factors, to pit areas (such as lake, sea and ocean floors). Sediments are mostly carried by water (flow process), wind (wind process) and glaciers
What does sedimentation depend on?
Sedimentation and climate relationship
Climate changes, such as more frequent and intense rain events, can increase erosion and cause greater amounts of sediment to spill into rivers, lakes and streams.
More frequent and heavy rain events can increase sediment loading from stormwater runoff. Stronger storms, higher river levels and faster flow rate can increase erosion and result in increased suspended sediment (turbidity) in water bodies and also affect the normal distribution of sediment along river, lake and stream beds. These climate impacts can strain efforts to preserve water quality through effective erosion and sediment control management efforts.
Excessive levels of suspended stream sediment (turbidity) or a change in sediment distribution from more frequent and intense storms can adversely affect ecosystem health.
regression code
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn import preprocessing, svm
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
df = pd.read_csv('DeltaX_GrainSizeDistribution_Atcha_Spring2021.csv')
df_binary = df[['water_velocity', 'sd_sediment_concentration_grainsize_832_913']]
# Taking only the selected two attributes from the dataset
df_binary.columns = ['water_velocity', 'sd_sediment_concentration_grainsize_832_913']
#display the first 5 rows
df_binary.head()
​
#plotting the Scatter plot to check relationship between water velocity and sediment concentiration
sns.lmplot(x ="water_velocity", y ="sd_sediment_concentration_grainsize_832_913", data = df_binary, order = 2, ci = None)
# Eliminating NaN or missing input numbers
df_binary.fillna(method ='ffill', inplace = True)
X = np.array(df_binary['water_velocity']).reshape(-1, 1)
y = np.array(df_binary['sd_sediment_concentration_grainsize_832_913']).reshape(-1, 1)
# Separating the data into independent and dependent variables
# Converting each dataframe into a numpy array
# since each dataframe contains only one column
df_binary.dropna(inplace = True)
# Dropping any rows with Nan values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25)
​
# Splitting the data into training and testing data
regr = LinearRegression()
regr.fit(X_train, y_train)
print(regr.score(X_test, y_test))
y_pred = regr.predict(X_test)
plt.scatter(X_test, y_test, color ='b')
plt.plot(X_test, y_pred, color ='k')
plt.show()
# Data scatter of predicted values
df_binary500 = df_binary[:][:500]
# Selecting the 1st 500 rows of the data
sns.lmplot(x ="water_velocity", y ="sd_sediment_concentration_grainsize_832_913", data = df_binary500,
order = 2, ci = None)
df_binary500.fillna(method ='ffill', inplace = True)
X = np.array(df_binary500['water_velocity']).reshape(-1, 1)
y = np.array(df_binary500['sd_sediment_concentration_grainsize_832_913']).reshape(-1, 1)
df_binary500.dropna(inplace = True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25)
regr = LinearRegression()
regr.fit(X_train, y_train)
print(regr.score(X_test, y_test))
y_pred = regr.predict(X_test)
plt.scatter(X_test, y_test, color ='b')
plt.plot(X_test, y_pred, color ='k')
plt.show()
from sklearn.metrics import mean_absolute_error,mean_squared_error
mae = mean_absolute_error(y_true=y_test,y_pred=y_pred)
#squared True returns MSE value, False returns RMSE value.
mse = mean_squared_error(y_true=y_test,y_pred=y_pred) #default=True
rmse = mean_squared_error(y_true=y_test,y_pred=y_pred,squared=False)
print("MAE:",mae)
print("MSE:",mse)
print("RMSE:",rmse)
Output of the code
#plotting the Scatter plot to check relationship between water velocity and sediment concentiration
