We have moved!

The bigger, better, brand new DAPA blog is here (link)


Please note this Blog is not updated anymore.

We have moved! -- CLICK HEREe --
Decision and Policy Analysis Research Area – DAPA

Data Dreaming

Coffee with: Daniel Jiménez

Daniel Jimenez is an Agronomic Engeneer and works with the Site Specific Agriculture group of DAPA.

We are the group of ‘Site Specific Agriculture’. Within this group we apply the principles of big data and methodologies. Big, because compared to traditional research in agriculture we often analyze thousands of sites covering a wide range of environmental conditions which, for agriculture, is a ‘BIG’ amount of data, which then explains again where the name is coming from.

The site-specific agriculture group uses information on harvesting events to understand the variability in production; based on the analysis of this information it generates knowledge for decision-makers in agriculture. Data on climate, soils and agronomic management are combined to identify the factors or combinations of factors that lead towards lower or higher productions. (Read here for more info). Its objective is to maximize the agricultural system.

Photocredit: Neil Palmer (CIAT)Important, and which makes us different from other data research groups, is that we have close dialogues with the end users of the products. We discuss the results with them, to be able to adapt them, vary them and re-use them. So it’s a fine combination between data-dreaming and discussing with the actual target-group.

We mostly work on how to collect, analyze and disseminate information. We work with both, information collected by ourselves or partners and information available, and this way we try to for example close the gaps, the so called ‘yield gap’. It is important to identify the role of the climate for this and how much of the yield variation/crop performance can be explained by this factor. Concerning climate change we work together with the team of CCAFS.

So, simpler put, part of what we do is to do what agronomist have been doing for over a century, which is from observations to identify what should be modified in order to maximize the productivity, but taking advantage of modern information technology and the data available all over,. We mostly use empirical models which given the information we use bring a lot of flexibility; it allows you to play with the information that is already available.

Photocredit: Neil Palmer (CIAT) Another tool that is important is the seasonal forecast. This tool provides information on which is the best crop to cultivate, which varieties. The crops we mainly work with are rice, maize and beans (in Colombia). In the past we also used to work with crops like avocado, citrus, plantain, mango and maize in Malawi and Kenya.

This work is very multidisciplinary, which makes it so much stronger than just each individuals work. We work together with many teams within CIAT. One of them is CCAFS, as mentioned before. We work a lot together with the rice program, agrobiodiversity and soil areas and within DAPA with the, Linking Farmers to Markets (LFM), and spatial and agricultural modelling:. Together with the LFM group for example we identify the potential zones of enabling environments and capable farmers.

Further reading:

http://www.slideshare.net/ciatdapa/big-data-ciat-april2014djetslideshare

http://www.slideshare.net/ciatdapa/uso-degrandes-datos-big-data-en-la-agricultura-caso-de-estudio-fedearroz-en-colombia

http://networkedblogs.com/RaeVm

http://www.ciat.org/index.php/es/blog/item/73-cuando-solo-tienes-10-minutos.html

http://irri.org/rice-today/where-latin-america-s-rice-gets-a-baptism-of-fire

A Survey of Artificial Neural Network-Based Modeling in Agroecology. (2008)

Analysis of Andean blackberry (Rubus glaucus) production models obtained by means of artificial neural networks exploiting information collected by small-scale growers in Colombia and publicly available meteorological data. (2009)

Interpretation of commercial production information: A case study of lulo (Solanum quitoense), an under-researched Andean fruit. (2011)

Enhancing Decision-Making Processes of Small Farmers in Tropical Crops by Means of Machine Learning Models. (2012)

Related Posts Plugin for WordPress, Blogger...
Share this:
about CIAT

If you could answer these three short questions, that would be really appreciated http://dapa.ciat.cgiar.org/we-want-to-know-our-readers/

Our Latest Presentations