Our project is concerned with identification of environmental threats that can add burden to public. These environmental threats can cause massive damage to the local as well as global economics. Since most people are in the lockdown and government is focusing on controlling the corona cases, it might be too late to act against these additional threats. However, this can be minimized if they have early detailed information so that they can act against it. For example: knowing the early possibility of landslides can save local lives and migrate their stored food
One such extreme environmental threat that is causing huge damage to the food system (at the time of writing) is LOCUST Attak in South Asia. Along with COVID-19 pandemic, climate shocks, conflict and acute food insecurity, East Africa and South-West Asia region now faces a hunger threat from Desert Locust. Due to the increasing number of cyclones followed near to the regions, very favourable conditions for desert Locusts to breed, grow and create, huge swarms have been created. The plague lead by the Locust has resulted in destroying a tremendous number of food crops ultimately leading to food scarcity in the regions.
Understanding the situation and how similar it is to the begin of the COVID19 situation (where we required easy access to the information), so we have targetted on monitoring the movement of LOCUST and have tried our best to forecast it as well. With the warning from FAO: "Heavy rains favour reproduction, the second wave of locusts expected during the upcoming harvest".
Therefore, it is of utmost importance to track their progress. With this information available through our website and app platform, the concerned person can track the current and future predicted migration path and start taking immediate precaution such that there is minimal damage to their belongings/livelihood. Our core target is to make the information available readily to the mass. Some forecast as well as the study on the LOCUST details in depth through our website can be done.
People in South Asia especially India, Pakistan and Nepal and Horns of Africa are fearing of the news of LOCUST attack. At the time of writing, Locust swarms is causing huge damage in food crops in Rajasthan area of India. At the same time, earthquakes are occuring frequently in himalayan areas of Nepal. While government is rightly focused on the covid-19, these environmental effects can also cause a massive burden to public. Simple put: COVID = LESS FOOD, LOCUST + COVID = MUCH LESS FOOD. Thus, we wanted to develop a model which uses data from NASA/ESA in order to predict these threats. We focused especially on LOCUST as this is the burning issue in South Asian and African Countries.
With the help of NASA's MODIS data available open we were able to understand the vegetation growth upon which the LOCUST feed and further with the open data from ESA 's Sentinal-1, it was easy to understand the rainfall pattern. Finally combining with the LOCUSTs' open data available by FAO we plotted the map, used LOCUST hub API to embed on our site as well. On detail analysis and study of the movement pattern, we forecasted the movement of LOCUST up to some extent as well.
Coding languages: Python, JavaScript
Software: Matlab, R, Jupyter Notebook
Thank you Hackathon Community for hosting our domain and website: https://huntersfromnasa.co/
Problems:
We overcame these problems by discussing with mentors in space chats.
Achivements:
DETAILED REPORT
PROBLEM: Worlds Population is increasing , going to be 9 billion soon. No of people to feed is increasing. On the other hand, there is famine or starvation in the world with todays 7 billion population. UN plans 17 SDGs. 1st is FOOD i.e. to reduce famine. While due to current COVID-19 situation, food production, distribution ,etc has been severely affected. If such worldwide lockdown situation has to be elongate, there will be severe food scarcity in the world.
Middle Eastern, Medditerinean and esp fertile land of Indo Pak South Asian Region is more severely affected during this time. Locust ( an insect) has returned in 27 years. It is destroying all the crops of people in that region. Due to COVID-19 fear and lockdown situation people haven't been able apply effective means/methods to get rid of them. For eg, some farmers in Pakistan started killing them manually and feeding them to their Poultry. It is massively supported and promoted by government. But, not much effective progress has been achieved. It is not the permanent solution. Locust are spreading very rapidly in those areas.
SOLUTION: We thought if we could track the movement/migration of Locust , and work according to those statistics, much effective measures can be acheived in controlling them. We study their suitable habitat comparing it to different factors like rainfall, temperature, soil moisture, green vegetation,etc and predict their next potential habitat.
We use Imageprocessing and some modern Machine Learning, Neural Networks , etc technique for data analysis for this prediction. We use those Image data and other data from NASA, MODIS, RAMSES, etc.
Desert locusts (Schistocerca gregaria) represent a major threat for agro-pastoral resources and food security over almost 30 million km2 from northern Africa to the Arabian peninsula and India. Given the differential food preferences of this insect pest and the extent and remoteness of the their distribution area, near-real-time remotely-sensed information on potential habitats support control operations by narrowing down field surveys to areas favorable for their development and prone to gregarization and outbreaks. The development of dynamic greenness maps, which detect the onset of photosynthetic vegetation, allowed national control centers to identify potential habitats to survey, as locusts prefer green and fresh vegetation. Their successful integration into the daily control operations led to a new need: the near-real-time identification of the onset of dryness, a synonym for the loss of habitat attractiveness, likely to be abandoned by locusts. The timely availability of this information would enable control centers to focus their surveys on areas more prone to gregarization, leading to more efficiency in the allocation of resources and in decision making. In this context, this work developed an original method to detect in near-real-time the onset of vegetation senescence. The design of the detection relies on the temporal behavior of two indices: the Normalized Difference Vegetation Index, depending on the green vegetation, and the Normalized Difference Tillage Index, sensitive to both green and dry vegetation. The method is demonstrated in Mauritania, an ever-affected country, with 10-day MODIS mean composites for the years 2010 and 2011. The discrimination performance of three classes (“growth”, “density reduction” and “drying”) were analyzed for three classification methods: maximum likelihood (61.4% of overall accuracy), decision tree (71.5%) and support vector machine (72.3%). The classification accuracy is heterogeneous in both time and space and is affected by several factors, such as vegetation density, the north-south climatic gradient and the relief. Smoothing the vegetation time series resulted in an increase of the overall accuracy of about 5% at the expense of a loss in timeliness of ten days. To simulate near-real-time monitoring conditions, the decision tree was applied to the decade of 2010. Overall, the seasonal vegetation cycle appeared clear and consistent. The results obtained pave the way for an operational implementation of the senescence dynamic mapping and, consequently, to further strengthen the capacity of the locust control management.
METHODS USED BY MODIS:
Support Vector Machine (72.3% Accuracy)
Decision Tree (71.5%)
OUR IDEA( Methods We used):
MODIS/Terra Vegetation Indices (MODIS land data products were used to monitor land processes such as vegetation cover and condition as well as surface temperatures)
MOD13C1 v006
MOD13C2 v006
Sentinel-1 ( The Sentinel-1 provided data for monitoring water, soil and agriculture. This data was used in combination with soil moisture data and other locusts relevant ancillary data to create valid indicators for locust monitoring and mapping.)
Copernicus
FAO / Locust Monitoring
Adult Locust
Swarms Locust
Locust Hub
Locust Watch