Search

Agricultural areas of Mediterranean regions host an extraordinary wealth of biodiversity and represent the source of income for a large population often living below the average economic conditions of the most advanced regions of Europe. In these areas, the semi-arid climates, the impact of climate change, the parcelization of land property, and the poor soils, contribute to create widespread conditions of low profitability of agricultural areas. This is likely to have an impact on the increasing occurrence of land abandonment phenomena and on growing hydrogeological risk linked to the lack of land maintenance. The productivity estimation of these agricultural areas represents a crucial information to detect hotspots of degradation helping policy makers in taking specific actions to increase productivity and reduce migration fluxes. In this work, realized in the framework of the ODESSA (On DEmand Services for Smart Agriculture) project (financed by the European Regional Development Fund Operational Programme 2014-2020 of Basilicata Region), the procedure adopted involves the use of climate and vegetation geospatial data, including both direct observational data (temperature, rainfall, etc.) and satellite-derived vegetation indexes. For the climatic component, we exploited a database of daily temperature and rainfall data (2000-2021) acquired by the agrometeorological network of ALSIA (Lucana Agency for Development and Innovation in Agriculture) and the CHIRPS (Climate Hazards Group InfraRed Precipitation with Station data) dataset providing rainfall data (1981-2020) at a spatial resolution of 0.050 to produce different diagnostic indices able to capture low-productivity areas. We tested this procedure in two districts of Basilicata (Southern Italy): the Vulture-Melfese and the Metapontino, representing the core areas of regional agricultural specialization for vineyards and intensive fruit and vegetable crops, respectively.

In the framework of the On Demand Services For Smart Agriculture (OD4SA) project, funded by PO FESR 2014-2020 from Regione Basilicata, Italy, a weather forecast service has been developed, for applications in smart agriculture and precision farming. It is based on the Weather Research and Forecasting (WRF) model and provides a daily 96-hour forecast of temperature and water vapor at 2 m altitude, wind speed and direction at 10 m altitude, atmospheric pressure, solar irradiance, and 1-hour accumulated rainfall, for the Southern Italy. Although encouraging advances in microscale modeling have been achieved in the last decade, the computational costs imposed by the state of the art do not allow for continuous operational forecasting at the sub-kilometer scale, useful for precision farming, especially in southern Italy that is characterized by a complex orography. To overcome this limit, an algorithm based on some Artificial Neural Networks (ANNs) has been developed, by using the WRF Large Eddy Simulation (LES) to build the training database at 240 m spatial resolution. Particular attention was paid to the analysis of the true spatial resolution of the WRF-LES outputs, to the definition of the ANNs topology and to the input selection, from over 250 inputs more than half has been discarded. The preliminary results show RMSE equal on average to 70% of those obtained by using the most common spatial interpolation methods.

The objective of this paper is to describe the development and evaluate the performance of a completely new version of the Passive microwave Neural network Precipitation Retrieval (PNPR v2), an algorithm based on a neural network approach, designed to retrieve the instantaneous surface precipitation rate using the cross-track Advanced Technology Microwave Sounder (ATMS) radiometer measurements. This algorithm, developed within the EUMETSAT H-SAF program, represents an evolution of the previous version (PNPR v1), developed for AMSU/MHS radiometers (and used and distributed operationally within H-SAF), with improvements aimed at exploiting the new precipitation-sensing capabilities of ATMS with respect to AMSU/MHS. In the design of the neural network the new ATMS channels compared to AMSU/MHS, and their combinations, including the brightness temperature differences in the water vapor absorption band, around 183 GHz, are considered. The algorithm is based on a single neural network, for all types of surface background, trained using a large database based on 94 cloud-resolving model simulations over the European and the African areas. The performance of PNPR v2 has been evaluated through an intercomparison of the instantaneous precipitation estimates with co-located estimates from the TRMM Precipitation Radar (TRMM-PR) and from the GPM Core Observatory Ku-band Precipitation Radar (GPM-KuPR). In the comparison with TRMM-PR, over the African area the statistical analysis was carried out for a 2-year (2013–2014) dataset of coincident observations over a regular grid at 0.5° × 0.5° resolution. The results have shown a good agreement between PNPR v2 and TRMM-PR for the different surface types. The correlation coefficient (CC) was equal to 0.69 over ocean and 0.71 over vegetated land (lower values were obtained over arid land and coast), and the root mean squared error (RMSE) was equal to 1.30 mm h−1 over ocean and 1.11 mm h−1 over vegetated land. The results showed a slight tendency to underestimate moderate to high precipitation, mostly over land, and overestimate moderate to light precipitation over ocean. Similar results were obtained for the comparison with GPM-KuPR over the European area (15 months, from March 2014 to May 2015 of coincident overpasses) with slightly lower CC (0.59 over vegetated land and 0.57 over ocean) and RMSE (0.82 mm h−1 over vegetated land and 0.71 mm h−1 over ocean), confirming a good agreement also between PNPR v2 and GPM-KuPR. The performance of PNPR v2 over the African area was also compared to that of PNPR v1. PNPR v2 has higher R over the different surfaces, with generally better estimation of low precipitation, mostly over ocean, thanks to improvements in the design of the neural network and also to the improved capabilities of ATMS compared to AMSU/MHS. Both versions of PNPR algorithm have shown a general consistency with the TRMM-PR.