Ka pū te rūhā, ka hao te rangatahi
Mana grows with the ability to distribute rather than accumulate, which not only drives productivity and provides group security but also encourages innovation and entrepreneurship as individuals seek to grow their personal mana.
Source
Mauri Toi
The development of the Kaitiaki Intelligence Platform would position Māori as the first movers in environmental intelligence, both nationally and internationally, continuing a tradition of innovation.
The Kaitiaki Intelligence Platform has been designed modularly, with each module covering a different environmental area. Each module can be built based on the level of urgency for the type of environmental data needed and the availability of resources. Different Māori organisations may wish to collaborate, with each concentrating on building a different module, which they then share - all while ensuring that they are designed according to the same design principles so they are interoperable. Conversely, a consortium of interested parties might build the platform collectively, sharing data warehousing and a common user interface. Regardless of the approach, data sovereignty and security must be taken seriously through layered data security.
Throughout the development, Māori environmental wisdom can underpin and guide the design and build of each component. This will ensure that Kaitiaki Intelligence Platforms focus on tauutuutu, restorative and reciprocal environmental management.
Trusts, incorporations, and iwi may want to add extra features beyond environmental sensing. This could include mapping critical cultural sites like marae, mahinga kai, or puna wai.
Considering the development costs for building each module and ongoing operational costs is essential.
“Adapting these modules to the local context requires two essential sets of data. Firstly, it necessitates high-quality, locally ground-truthed environmental data specific to a particular area (which may include mātauranga-derived data), along with relevant remote sensing data (such as optical, multispectral, or radar satellite imagery) covering the same region. This ground-truth data serves a dual purpose: it is initially used as training data for the models, allowing them to adapt to the new landscapes and signatures observed in the satellite data; additionally, it is employed to validate the model’s outputs and assess its accuracy. The process of constructing these models is iterative.
”
