Add prerequisites for some theses

content/education/theses/2023-12-12-bam-aerial/index.md

@@ -11,4 +11,6 @@ The aim of this thesis is to leverage aerial data for the automatic mapping of a
 
 In order to use the LMA data in a mapping algorithm, it needs to be cleaned, processed and cropped into smaller patches. Subsequently, the student can choose among a number of Machine Learning or Deep Learning methods and train them on the data in order to obtain an accurate perimeter of the burn scar. The model(s) will also be evaluated using appropriate performance metrics.
 
+Prerequisites: Strong Python skills
+
 Supervisor: Maria Sdraka

content/education/theses/2023-12-12-floga-extend/index.md

@@ -13,6 +13,8 @@ The aim of this thesis is to extend the FLOGA dataset with several other wildfir
 
 Subsequently, the BAM-CD model will be finetuned on the new data and its performance will be assessed.
 
+Prerequisites: Strong Python skills
+
 Supervisor: Maria Sdraka
 
 [1] https://arxiv.org/abs/2311.03339 <br>

content/education/theses/2023-12-12-floga-modis/index.md

@@ -11,6 +11,8 @@ Orion Lab has assembled a novel benchmark dataset, namely FLOGA [1], for the map
 
 Since BAM-CD is only trained on Sentinel-2 data, it is able to produce high-resolution burn scar mappings but can only be used when clear images are provided both for the pre- and the post-fire status. The Sentinel-2 satellites have a temporal resolution of ~5 days, i.e. a new image of a specific region is captured every 5 days, rendering our method incapable of rapid, near real-time damage assessment. Therefore, the aim of this thesis is to train Machine Learning or Deep Learning models only on MODIS data, which have a temporal resolution of 1 day. Such a model will be able to provide a quicker evaluation of the burnt area and allow local authorities and forest scientists to formulate effective response and recovery strategies for the affected ecosystem and communities.
 
+Prerequisites: Strong Python skills
+
 Supervisor: Maria Sdraka
 
 [1] https://arxiv.org/abs/2311.03339

content/education/theses/2023-12-12-floga-sar/index.md

@@ -15,6 +15,8 @@ The aim of this thesis is to extend the FLOGA dataset with SAR data. For each ev
 
 Subsequently, the BAM-CD model or any other model of the student’s choice will be trained on the new SAR data and its performance will be assessed.
 
+Prerequisites: Strong Python skills
+
 Supervisor: Maria Sdraka
 
 [1] https://arxiv.org/abs/2311.03339