diff --git a/results/appendix/contributions.qmd b/results/appendix/contributions.qmd index 3d75790..154d496 100644 --- a/results/appendix/contributions.qmd +++ b/results/appendix/contributions.qmd @@ -4,31 +4,22 @@ Most of the work was done in pair programming. In the following sections we high ### Frederick -My contributions to the project encompassed several key areas: data acquisition, preprocessing, visualization, random forest implementation, and canopy height modeling. Each of these tasks presented unique challenges and learning opportunities. +My contributions to the project encompassed several areas: data acquisition, preprocessing, visualization, random forest implementation, and canopy height modeling. -#### Data Acquisition +In data acquisition, I sourced relevant datasets, particularly focusing on obtaining patches where one tree species exhibited dominance, navigating through existing datasets such as the *Waldmonitor* dataset and utilizing maps indicating dominant tree species in Nordrhein-Westfalia (NRW). Ensuring the validity of the selected patches, considering factors such as patch size and species diversity was a challenge I faced, teaching me the importance of meticulous data selection and validation. -My role in data acquisition involved sourcing relevant datasets for our study, particularly focusing on obtaining patches where one tree species exhibited dominance. This process involved navigating through existing datasets such as the *Waldmonitor* dataset and utilizing maps indicating dominant tree species in Nordrhein-Westfalia (NRW). One of the challenges encountered was ensuring the validity of the selected patches, considering factors such as patch size, species diversity, and the absence of human-made structures. Through this process, I learned the importance of meticulous data selection and validation to ensure the integrity of subsequent analyses. +Preprocessing involved essential steps such as tiling and height normalization to standardize the data and facilitate further analysis, with the challenge lying in optimizing these steps to retain relevant information while minimizing noise and artifacts, deepening my understanding of data standardization's impact on downstream analyses. -#### Preprocessing: Tiling/Height Normalization +Visualizing the data through density plots and boxplots was instrumental in gaining insights into the distribution and characteristics of the variables under study, with the challenge being to balance clarity and complexity, enhancing my visualization skills and effective communication of key findings. -Preprocessing the acquired data was essential to derive meaningful variables for analysis. Tiling and height normalization were particularly crucial steps to standardize the data and facilitate further analysis. Tiling involved partitioning the patches into smaller, manageable units, while height normalization ensured consistency in height measurements across different patches. This process taught me the importance of data standardization and the impact it can have on downstream analyses. +Implementing the Random Forest algorithm for species classification involved model training, validation, and performance evaluation, with generating scores and confusion matrices allowing us to assess the model's accuracy and identify areas for improvement, deepening my understanding of machine learning techniques. -#### Visualization: Density and Boxplot +Developing a canopy height model provided valuable insights into remote sensing techniques and their applicability in forestry research. -Visualizing the data through density plots and boxplots was instrumental in gaining insights into the distribution and characteristics of the variables under study. Creating informative visualizations required careful selection of plotting parameters and consideration of the audience's interpretation. Balancing clarity and complexity posed a challenge, but it also provided an opportunity to enhance my visualization skills and effectively communicate key findings. - -#### Random Forest: Scores and Confusion Matrix - -Implementing the Random Forest algorithm for species classification involved several steps, including model training, validation, and performance evaluation. Generating scores and confusion matrices allowed us to assess the model's accuracy and identify areas for improvement. - -#### Canopy Height Model - -Developing a canopy height model involved integrating data from various sources to estimate the height of forest canopies. Overcoming technical challenges and refining the model parameters provided valuable insights into remote sensing techniques and their applicability in forestry research. - -In summary, my contributions to the project encompassed a range of tasks, each presenting its own set of challenges and learning opportunities. From data acquisition to model implementation, I gained valuable experience in ecological research methods and data analysis techniques. +Overall, my contributions to the project have enriched my skills and knowledge in research methods and data analysis techniques, contributing to the project's success while broadening my expertise in the field of forestry and environmental science. ### Jakob + In the broader context of a comprehensive lidar data analysis project, my contributions were instrumental in advancing key components. The preprocessing phase saw enhancements in Intersection, Detection, and Segmentation processes. I played a pivotal role in refining Intersection by overlaying lidar data onto shapefiles, ensuring a coherent file structure. Additionally, my efforts in Detection focused on optimizing tree identification within the intersected data. I developed the tree Segmentation too. In terms of visualization, my contributions elevated the understanding of lidar data. The presentation of the confusion matrix as a colored table provided a comprehensive view of classification performance. Through the implementation of bar plots for patch-level data, I contributed to insights into the distribution of features. Precision and recall metrics were effectively communicated via bar plots, offering a nuanced evaluation of the model's performance. The integration of Canopy Height Plots further enriched the visual representation of canopy structures.