adding data

data/guanacoElaborationOutput.txt

@@ -0,0 +1,10 @@
+The purpose of studying novel fast super resolution convolutional neural network (SRCNN) and earth system model (ESM) is to improve the quality of images and to better understand the Earth's climate system.
+
+SRCNN is a type of deep learning algorithm that is used to enhance the resolution of low-quality images. It does this by using a convolutional neural network to analyze the image and then apply a series of filters to increase the resolution. SRCNN has been used in a variety of applications, including medical imaging, aerial photography, and security surveillance.
+
+ESM is a computer model that is used to simulate and predict the behavior of the Earth's climate system. It includes components such as the atmosphere, oceans, land surface, and ice sheets, and it is used to study issues such as global warming, El Niño, and hurricane formation. ESMs are used by scientists to better understand the climate system and to make predictions about its future behavior.
+
+The areas of application for SRCNN and ESM include:
+
+1. Medical imaging: SRCNN can be used to enhance the resolution of medical images, such as X-rays, CT scans, and MRI scans, to better diagnose and treat diseases.
+2.

data/guanacoSummaryOutput.txt

@@ -0,0 +1,7 @@
+The main idea of the paper is to use a type of artificial intelligence called a "convolutional neural network" to upscale or "super resolve" the resolution of a computer model of the Earth's climate. The authors call their network FSRCNN, which stands for "fast super resolution convolutional neural network".
+
+The Earth's climate is modeled using a computer program called an ESM, which stands for "earth system model". ESMs are very complex programs that try to simulate how the different parts of the Earth system, such as the atmosphere, oceans, and land, interact with each other. However, ESMs are often limited in the resolution they can simulate. This means that they can only model a certain number of grid cells or pixels, and each cell or pixel represents a small area of the Earth.
+
+The authors of this paper wanted to use ESMs to study how the Earth's climate might change in the future. To do this, they needed to upscale the resolution of their ESMs so that they could study smaller-scale features, such as the behavior of individual clouds or the impact of localized changes in the climate.
+
+The authors developed FSRCNN to do this upscaling. FSRCNN is a type of neural network that is trained to learn how to upscale images.

data/inputToGuanaco.txt

@@ -0,0 +1 @@
+Batch Active Learning for Multispectral and Hyperspectral Image Segmentation Using Similarity Graphs. Graph learning, when used as a semi-supervised learning (SSL) method, performs well for classification tasks with a low label rate. We provide a graph-based batch active learning pipeline for pixel/patch neighborhood multi- or hyperspectral image segmentation. 

data/sample-data.clf.jsonl

@@ -0,0 +1 @@
+{"target":["Graph learning, when used as a semi-supervised learning (SSL) method, performs well for classification tasks with a low label rate.","We provide a graph-based batch active learning pipeline for pixel\/patch neighborhood multi- or hyperspectral image segmentation.","Our batch active learning approach selects a collection of unlabeled pixels that satisfy a graph local maximum constraint for the active learning acquisition function that determines the relative importance of each pixel to the classification.","This work builds on recent advances in the design of novel active learning acquisition functions (e.g., the Model Change approach in arXiv:2110.07739) while adding important further developments including patch-neighborhood image analysis and batch active learning methods to further increase the accuracy and greatly increase the computational efficiency of these methods.","In addition to improvements in the accuracy, our approach can greatly reduce the number of labeled pixels needed to achieve the same level of the accuracy based on randomly selected labeled pixels."],"title":"Batch Active Learning for Multispectral and Hyperspectral Image Segmentation Using Similarity Graphs","contrib_indices":[1,2,3,4]}

data/sample-data.jsonl

@@ -0,0 +1 @@
+{"target":["We present the first application of a fast super resolution convolutional neural network (FSRCNN) based approach for downscaling earth system model (ESM) simulations.","Unlike other SR approaches, FSRCNN uses the same input feature dimensions as the low resolution input.","This allows it to have smaller convolution layers, avoiding over-smoothing, and reducing computational costs.","We adapt the FSRCNN to improve reconstruction on ESM data, we term the FSRCNN-ESM.","We use high-resolution (\u223c0.25\u00b0) monthly averaged model output of five surface variables over North America from the US Department of Energy's Energy Exascale Earth System Model's control simulation.","These high-resolution and corresponding coarsened low-resolution (\u223c1\u00b0) pairs of images are used to train the FSRCNN-ESM and evaluate its use as a downscaling approach.","We find that FSRCNN-ESM outperforms FSRCNN and other super-resolution methods in reconstructing high resolution images producing finer spatial scale features with better accuracy for surface temperature, surface radiative fluxes, and precipitation."],"title":"Reconstructing High Resolution ESM Data Through a Novel Fast Super Resolution Convolutional Neural Network (FSRCNN)"}