review_update_1

Author: sdash77

samples/04_gis_analysts_data_scientists/cloud_removal_using_pre-trained_deep_learning_model_and_raster_function.ipynb

@@ -39,9 +39,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The goal of this notebook, is to detect and replace the cloud contaminated region of the satellite images. As clouds create obstruction in generating results from the imagery such as land cover classification, time series analysis etc.  In a general perspective, it can be seen as a image denoising problem, in which clouds are considered as noise in respect to land surface in images. \n",
+    "The goal of this notebook, is to detect and replace the cloud contaminated region of the satellite images. Clouds often create obstructions in satellite imagery that can hinder results in processes like land cover classification and time series analysis. In a general perspective, it can be seen as a image denoising problem, in which clouds are considered as noise in respect to land surface in images. \n",
     "\n",
-    "The notebook, we demonstrates a way of combining pre-trained deep learning model available in living atlas and image processing technique available in [raster functions](https://github.com/Esri/raster-functions) to remove clouds from satellite imagery. "
+    "In this notebook, we will detect and replace cloud contaminated regions of satellite imagery by combining a pre-trained deep learning model, available in living atlas, and an image processing technique, available in [raster functions](https://github.com/Esri/raster-functions)."
    ]
   },
   {
@@ -62,7 +62,7 @@
    "outputs": [],
    "source": [
     "import matplotlib.pyplot as plt\n",
-    "#import arcpy\n",
+    "import arcpy\n",
     "from arcgis import GIS\n",
     "from arcgis.learn import prepare_data, Pix2PixHD, Pix2Pix"
    ]
@@ -186,14 +186,14 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Use cloud mask generation pre-trained model"
+    "### Use the pre-trained cloud mask generation model"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Cloud mask generation pre-trained model, trained on sentinel-L2A imagery is used to generate cloud mask for input raster. The cloud mask is used by Stepwise local radiometric adjustment (SLRA) raster function as guidance for removal of cloud-contaminated pixels in the target raster."
+    "The pre-trained cloud mask generation model has been trained on sentinel-L2A imagery and is used to generate a cloud mask for an input raster. The cloud mask will be used by a Stepwise local radiometric adjustment (SLRA) raster function as guidance for removing cloud contaminated pixels from the target raster."
    ]
   },
   {
@@ -238,14 +238,14 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Reclassify cloud types in cloud mask"
+    "### Reclassify cloud types in the cloud mask"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Cloud are classfied into high, medium, and low density. As all types of clouds detected by the pre-trained model need to be removed. Hence, its reclassified into a single class."
+    "The pre-trained cloud mask model will classify clouds into 3 classes. low, medium, and high density. As we want to remove all cloud contaminated regions, we will reclassify these 3 classes into one single class."
    ]
   },
   {
@@ -305,21 +305,21 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Use stepwise local radiometric adjustment raster function"
+    "## Use the stepwise local radiometric adjustment raster function"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "This Python raster function is for blending areas using Stepwise Local Radiometric Adjustment algorithm [1](https://www.mdpi.com/517118). The stepwise local radiometric adjustment is undertaken to fill contaminated areas and is conducted on each mask region of the target image. This tool replaces those pixels which are covered with clouds using the replacement raster. \n",
+    "Next, we will use the Python raster function to blend areas using a Stepwise Local Radiometric Adjustment algorithm [Li .et al, 2019](https://www.mdpi.com/517118). Stepwise Local Radiometric Adjustment is used to fill contaminated areas and is performed on each mask region of the target image. Using the replacement raster, the tool will replace pixels that are covered with clouds. \n",
     "\n",
-    "The raster functions can be downloaded as python(.py) file from [raster-functions](https://github.com/Esri/raster-functions/blob/master/functions/StepwiseLocalRadiometricAdjustment.py), available inside the functions folder. StepwiseLocalRadiometricAdjustment.py can be opened using `Open Python Raster function` in pane. Then, it is saved using `Save As`. `Size of Window` and `Buffer Mask` can be experimented with values for varying results according to requirements and cloud coverage.\n",
+    "The raster functions can be downloaded as a python(.py) file [raster-functions](https://github.com/Esri/raster-functions/blob/master/functions/StepwiseLocalRadiometricAdjustment.py) in the functions folder. StepwiseLocalRadiometricAdjustment.py can be opened using `Open Python Raster function`. Once opened, save it using `Save As`. `Size of Window` and `Buffer Mask` can be experimented with values for varying results according to requirements and cloud coverage. Next, you can experiment with different values for the Size of Window and Buffer Mask parameters, depending on the requirements and cloud coverage of your use case.\n",
     "\n",
     "- `Input Raster`: cloud covered imagery\n",
     "- `Input Replacement raster`: replacement raster\n",
     "- `Input Mask`: generated cloud mask\n",
-    "- `Size of Window`: default set to 80, can be any multiples of 20\n",
+    "- `Size of Window`: default set to 80, can be any multiple of 20\n",
     "- `Buffer Mask`: any value between 0-15, accordiong to coverage of cloud mask"
    ]
   },
@@ -334,7 +334,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The saved raster function is exported as rft(raster function template). rft is used in `Generate Raster From Raster Function` tool to get the final results as this tool is designed for raster processing using multiple threads to help speed up the processing."
+    "The saved raster function can then be exported as an rft(raster function template). rft is used in the `Generate Raster From Raster Function` tool to get the final results, as this tool is designed for raster processing using multiple threads to help speed up the processing."
    ]
   },
   {
@@ -370,7 +370,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "In this notebook, we demonstrated a way to remove clouds from satellite imagery with a combination of pre-trained deep learning model and esri raster function. It also revels how we can use our developed python raster functions in arcgis pro. "
+    "In this notebook, we have demonstrated a method to remove clouds from satellite imagery with a combination of a pre-trained deep learning model and Esri raster functions. Further, it demonstrated how you can use your developed python raster functions in ArcGIS Pro."
    ]
   },
   {