As Hitsoft R&D team, we produce effective tools, models and solutions with technologies of artificial intelligence, machine learning, deep learning and blockchain by aiming to provide solutions to the problems that are critical for businesses and future of the world. We already completed five projects and are conducting two more for both public and private sector organizations.

In ODC challenge we teamed up as four; Bulent is our Project Manager who has Mathematics and MBA degrees with his fifteen years of experience in technical and management roles on software architecture, intelligent systems, artificial intelligence and team management in finance, banking and energy sectors. Gulsen is our Analyst and concept developer on sustainability, social innovation and project experience about industrial systems, environment, technologies, impact analysis, business/market model and project design for eight years with her Environmental, Industrial MEng. and Management Engineer, MSc background. Ersin is our software specialist who is responsible of software development and visualization leveraging data science for 2 years.

Emre is our recent member who has a deep knowledge of artificial intelligence more than a decade with his data science, ML, computer vision, analytics and entrepreneur as well as project and product development background.

In R&D Center we are a highly motivated team that consists of data scientists, analysts, sustainability expert, developers and project managers as well as university collaborators.

Hi-Terra is designed as a platform which will perform data processing to generate forecasts of soil moisture and watering. Since it has a dynamically learning capacity, the model is able to improve the forecast performance and to iteratively advance itself by using more data sets. It constitutes a sensitive, intelligent and reliable platform to produce forecasts for users both to get insights about soil moisture, watering time, to be notified about severe weather conditions, irrigation needs or water level anomalies and furthermore water amount for irrigation.

Hi-Terra provides resource efficient, cost effective and easy-to-use solution while taking its unique characteristic from the deep learning algorithms in its core. Hi-Terra, as an infrastructure, has a capability to be used within a wide spectrum of application areas from personal landscapes (gardens, yards), greenhouses, fields to golf courses, greens. While creating a positive environmental impact by saving water, relatedly crops through soil moisture insights, helps to generate societal and economic outcomes by addressing water, food challenges, excess cost burdens and environmental well-being.

We used the Soil Moisture Data from GROW project.

While experiencing the complexity, the climate change phenomenon affects our lives even the future generations with its impacts in terms of environmental, social and economic perspectives where sustainability takes its roots. From our point of view, in a data-driven world, it is closely related to the attributes, moreover, our attitudes which causes alterations in the system and impact for overcoming the climate change consequences while building our common future. So, we believe that citizen science has a great value and power as the small efforts count to tackle the challenges, to gather data to achieve meaningful insights and to spread the impact from a person to the world where everything is connected.

This era of change reveals the new opportunities and the challenges hand in hand to rethink how to grow, share and consume. The key is the emerging and cutting-edge technologies that are leverages to adapt, to participate to the solution and create a positive impact. In ODC, as a great opportunity to experience to observe, we started with soil moisture and discovered how it is a strong parameter to dive deeper and even how one parameter affects the multiple systems. In these terms, the dynamism of technology and society-driven landscape indicate for all of us the opportunities to redesign, discover and innovate.