3. Producción
Browse
5 results
Search Results
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Exploring machine learning techniques to predict deforestation to enhance the decision-making of road construction projects(Wiley, 2021-08-24)Land use changes (LUCs), which are defined as the modification in the use of land due to anthropogenic activities, are important sources of GHG emissions. In this context, understanding future trends of LUCs, such as deforestation, in a spatial manner is relevant. The main objective of this study is to generate a deforestation prediction model for a given period of time (i.e., 2002–2017 and 2010–2017) to estimate the potential carbon emissions associated with different anthropogenic variables in the Peruvian Amazon using machine learning (ML) algorithms. This study was motivated in the analysis of a road project previously studied using life cycle assessment (LCA). Models using neural networks and random forest algorithms were trained and evaluated in a fully cloud-based environment using Google Earth Engine. ML-related results demonstrated that random forest is a quicker and straightforward response to model the system under study, especially considering that data do not require additional processing during the modeling and prediction stages. Predicted results suggest that expected road expansion may be related to considerable carbon emissions in the future. Calculated values are relevant especially if the mitigation efforts that Peru has complied with in the Paris Agreement are considered. The increased complexity of the framework is justified since it allows identifying the location of hotspots and may potentially complement the utility of LCA in policy support in the areas of territorial planning and tropical road expansion. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Big data analytics for critical information classification in online social networks using classifier chains(Springer, 2022-01-01)Industrial and academic organizations are using online social network (OSN) for different purposes, such as social and economic aspects. Now, OSN is a new mean of obtaining information from people about their preferences, and interests. Due to the large volume of user-generated content, researchers use various techniques, such as sentiment analysis or data mining to evaluate this information automatically. However, the sentiment analysis of OSN content is performed by different methods, but there are some problems to obtain highly reliable results, mainly because of the lack of user profile information, such as gender and age. In this work, a novel dataset is built, which contains the writing characteristics of 160,000 users of the Twitter OSN. Before creating classification models with Machine Learning (ML) techniques, feature transformation and feature selection methods are applied to determine the most relevant set of characteristics. To create the models, the Classifier Chain (CC) transformation technique and different machine learning algorithms are applied to the training set. Simulation results show that the Random Forest, XGBoost and Decision Tree algorithms obtain the best performance results. In the testing phase, these algorithms reached Hamming Loss values of 0.033, 0.033, and 0.034, respectively, and all of them reached the same F1 micro-average value equal to 0.976. Therefore, our proposal based on a multidimensional learning technique using CC transformation overcomes other similar proposals. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Seasonal Water Storage and Release Dynamics of Bofedal Wetlands in the Central Andes(John Wiley and Sons Ltd, 2023-08-01)Tropical high-Andean wetlands, locally known as ‘bofedales’, are key ecosystems sustaining biodiversity, carbon sequestration, water provision and livestock farming. Bofedales' contribution to dry season baseflows and sustaining water quality is crucial for downstream water security. The sensitivity of bofedales to climatic and anthropogenic disturbances is therefore of growing concern for watershed management. This study aims to understand seasonal water storage and release characteristics of bofedales by combining remote sensing analysis and ground-based monitoring for the wet and dry seasons of late 2019 to early 2021, using the glacierised Vilcanota-Urubamba basin (Southern Peru) as a case study. A network of five ultrasound loggers was installed to obtain discharge and water table data from bofedal sites across two headwater catchments. The seasonal extent of bofedales was mapped by applying a supervised machine learning model using Random Forest on imagery from Sentinel-2 and NASADEM. We identified high seasonal variability in bofedal area with a total of 3.5% and 10.6% of each catchment area, respectively, at the end of the dry season (2020), which increased to 15.1% and 16.9%, respectively, at the end of the following wet season (2021). The hydrological observations and bofedal maps were combined into a hydrological conceptual model to estimate the storage and release characteristics of the bofedales, and their contribution to runoff at the catchment scale. Estimated lag times between 1 and 32 days indicate a prolonged bofedal flow contribution throughout the dry season (about 74% of total flow). Thus, our results suggest that bofedales provide substantial contribution to dry season baseflow, water flow regulation and storage. These findings highlight the importance of including bofedales in local water management strategies and adaptation interventions including nature-based solutions that seek to support long-term water security in seasonally dry and rapidly changing Andean catchments. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Application of Machine Learning Algorithms to Classify Peruvian Pisco Varieties Using an Electronic Nose(Multidisciplinary Digital Publishing Institute (MDPI), 2023-07-01)Pisco is an alcoholic beverage obtained from grape juice distillation. Considered the flagship drink of Peru, it is produced following strict and specific quality standards. In this work, sensing results for volatile compounds in pisco, obtained with an electronic nose, were analyzed through the application of machine learning algorithms for the differentiation of pisco varieties. This differentiation aids in verifying beverage quality, considering the parameters established in its Designation of Origin”. For signal processing, neural networks, multiclass support vector machines and random forest machine learning algorithms were implemented in MATLAB. In addition, data augmentation was performed using a proposed procedure based on interpolation–extrapolation. All algorithms trained with augmented data showed an increase in performance and more reliable predictions compared to those trained with raw data. From the comparison of these results, it was found that the best performance was achieved with neural networks. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, A Machine Learning Approach to Understand How Accessibility Influences Alluvial Gold Mining Expansion in the Peruvian Amazon(Elsevier Ltd, 2023-06-01)Alluvial small-scale gold mining (ASGM) mining in the Amazon is expanding fiercely, generating severe environmental degradation, which includes the fast disappearance of primary forests in a highly biodiverse area of the world. Different factors motivate the growth of mining in the areas and understanding this expansion is important to safeguard protected areas or implement strategies to mitigate the related social and environmental impacts. Thus, the goal of this study is to apply machine learning techniques to explore gold mining expansion in Madre de Dios, in the Peruvian Amazon, and to identify possible future hotspots of these activities. Using an unsupervised learning algorithm and a random forest classification model, past expansion trends were analyzed and an explicit geo-spatial model was built. Results demonstrate that proximity to infrastructure is not always indicative of high mining probability. In fact, when analyzing the spatial distribution of model accuracy, it is observed that model performance decreases in clusters where accessibility and mining activity showed opposite trends. In contrast, the models yield accuracies greater than 0.9 when accessibility-related variables stand out as the most important. The model, which is flexible and reproducible, demonstrates to be useful to enhance decision making when implementing geo-spatial policies to address the problem of ASGM expansion in the Amazon.