Conference Agenda

The work conducted in these three years of activity aims to make a quantitative use of remote sensing information in agriculture and to develop products targeted at optimizing the production and allowing a more sustainable agriculture (e.g. optimization in the use of fertilizers and pesticides). The project has been concentrated on the following themes: retrieval of biophysical variables of vegetation, estimation of bare soil properties, prediction of crop yield and monitoring pest and diseases. The project included three sites, Maccarese farm in Central Italy, some site in Central East-Africa, a site in the middle East and farms in the Quzhou district in China city of Handan, in the south of Hebei Province.

For vegetation physical and chemical parameters, taking advantage of the PRISMA and ENMAP EO data, the work is aiming to use the potential oh hyperspectral data in deriving biophysical parameter related to equivalent water thickness (EWT). In particular, we aim to retrieve EWT by using a constrain minimization procedure applying the Beer-Lambert law in the 940-1100nm range to derive the optically leaf active water layer in cm. The EWT retrieved with the minimization procedure are compared with the one retrieved by using the hybrid approach (i.e. radiative simulation and Machine Learning Regression). Test site are in central Italy, and in the far East.

For topsoil characterization, the purpose of this activity was to investigate the suitability of PRISMA and Sentinel-2 images for the retrieval of topsoil properties such as Soil Organic Matter, and nutrients like Nitrogen, Phosphorus, Potassium and pH in croplands. Procedure is based on different Machine Learning (ML) algorithms and spectra pre-treatment. Results in the study area located in the north-eastern China near the prefecture-level city of Handan, in the south of Hebei Province, revealed better accuracies in retrieving topsoil properties obtained by PRISMA data instead to the Sentinel-2 data.

For crop yield prediction, we generated a 30-m Chinese winter wheat yield dataset (ChinaWheatYield30m) for major winter wheat-producing provinces in China for the period 2016–2021 with a semi-mechanistic model (hierarchical linear model, HLM). The yield prediction model was built by considering the wheat growth status and climatic factors. It can estimate wheat yield with excellent accuracy and low cost using a combination of satellite observations and regional meteorological information (i.e., Landsat 8, Sentinel-2 and ERA5 data from the Google Earth Engine (GEE) platform). The results were validated by using in situ measurements and census statistics and indicated a stable performance of the HLM model based on calibration datasets across China, with r of 0.81** and nRMSE of 12.59 %. With regards to validation, the ChinaWheatYield30m dataset was highly consistent with in situ measurement data and census data, indicated by r (nRMSE) of 0.72** (15.34 %) and 0.73** (19.41 %). With its high spatial resolution and accuracy, the ChinaWheatYield30m is a valuable dataset that can support numerous applications, including crop production modeling and regional climate evaluation.

For what concerns crop threats, the core of the system aiming at detecting yellow rust outbreaks in maize and wheat crops, will be built on PRISMA satellite. Several VIs (NDVI, SIPI, PRI, PSRI, MSR) computed by using hyperspectral images will be used to implement a Diseases Infection Index. The DI will be classified into four classes including healthy (DI≤5%), slight infection (5<DI≤20%), moderate infection (20<DI≤50%), and severe infection (DI>50%). It should be underlined that the algorithms proposed by Guo et al. (2021) have been developed based on hyperspectral images acquired by drones. The impact of spatial resolution on the capability to detect yellow rust in crops will be one of the results of the activity.

In addition, we have established the remote sensing-based risk assessment methods for agricultural pests, specifically for grasshopper and desert locust. For grasshopper, we took the two steppe types of Xilingol (the Inner Mongolia Autonomous Region of China) as the research object and coupled them with the MaxEnt and multisource remote sensing data to establish a remote sensing monitoring model for grasshopper potential habitat. The results demonstrated that the most suitable and moderately suitable areas were distributed mainly in the southern part of the meadow steppe and the eastern and southern parts of the typical steppe. We also found that the soil temperature in the egg stage, the vegetation type, the soil type, and the precipitation amount in the nymph stage were significant factors both in the meadow and typical steppes. For desert locust presence risk forecasting, we have proposed a dynamic prediction method of desert locust presence risk at Somalia-Ethiopia-Kenya. Monthly prediction experiments from February to December 2020 were conducted, extracting high, medium and low risk areas of desert locust occurrence in the study area. Results demonstrated that the overall accuracy was 77.46%, and the model enables daily dynamic forecasting of desert locust risk up to 16 days in advance, providing early warning and decision support for preventive ground control measures for the desert locust.

In summary, as of the third year of the Dragon 5, the project's execution progress is consistent with the schedule, and most of the activities have achieved good results. Additionally, some scholars in the project team are conducting scientific research using the data obtained through the cooperation between the two sides.

.