Blogs

Impact Analysis (April - October 2021)

Last 6 Months have taught us so much at Farmonaut. We faced the dangerous 2nd wave of covid-19 which affected all of us on the team as well as family level. For a bootstrapped startup like Farmonaut® it was a very important battle to be fought. It feels great to see us achieve so many milestones even in these tough times.


From serving more than 20,000 users directly through our platforms, to onboarding so many API users globally (Zr3i.com زرعي دوت, Godrej Agrovet Ltd, Ubincore, Fashion For Biodiversity Solutions GmbH, Linx Spatial Systems) and having more than 250,000 API Hits, to mapping 22,000+ farms for Godrej Agrovet Ltd, to successfully completely a large scale soybean area estimation for The Soybean Processors Association of India (SOPA), to conducting several internal and corporate researches, and receiving multiple awards and recognitions (Ramaiah Evolute, CE Worldwide, The Startup Pill, GIS Resources, Global Launch Base), it surely was a splendid 6 months period.


These are just a few steps towards a greater goal we plan to achieve in the coming months. Stay tuned! A lot more announcements are on the way.


Happy Farming!

#farming #farm #harvest #agrotech #agriculture #satellite #crophealth #farmonaut #fruit #vegetables #crops #agritech #precisionagriculture #organicfarming #greentech #technology #tech #foodsecurity #farmerlife #urbanfarmer #urbanfarming #nasa #remotesensing #gis #earth

We will keep posting about any such informative information on to our blogs, to help as many people as possible. Farmonaut is built upon a vision to bridge the technological gap between farmers and strives to bring state-of-the-art technologies in the hands of each and every farmer. For any queries/suggestions, please contact us at support@farmonaut.com.

We have some more interesting articles coming up soon. Stay tuned!

Wait!!

Before that…

Follow us at:

Facebook: https://facebook.com/farmonaut

Instagram: https://instagram.com/farmonaut

Twitter: https://twitter.com/farmonaut

LinkedIn: https://www.linkedin.com/company/farmonaut/

Pinterest: https://in.pinterest.com/farmonaut/

Tumblr: https://farmonaut.tumblr.com/

Youtube: https://www.youtube.com/channel/UCYWOOPPKATLgh4L6YRlYFOQ

AppLink: https://play.google.com/store/apps/details?id=com.farmonaut.android

Website: https://farmonaut.com

Satellite Imagery: https://farmonaut.com/satellite-imagery

Satellite Imagery Samples: https://farmonaut.com/satellite-imagery-samples

 

 

Rice Yield Calculation Based on Remote Sensing in Saharsa (Bihar) - 2021

Yield calculation of the crop is very important for assessing the production and it depends on many variables like soil, location, weather, crop variety, agricultural practices (date of planting, amount of irrigation, fertilizer use, weedicide and pesticide use), seeds and biotic stress. 

Remote sensing provides an effective and efficient way to forecast yield. Remote sensing has been widely used by many institutions across world to calculate area and yield of a crop.

In this paper, we focus on forecasting yield of paddy based on data from Sentinel-2 satellite data and Farmonaut’s Satellite Based Crop Monitoring System available on android, iOS, and web-app. The study area was rice crop in Saharsa (Bihar). The crop is in advanced stage and has vegetated fully and harvest is expected in next 10-30 days depending on crop variety of rice.

 

Methodology:

Data from Sentinel-2 was used and fields with highest vegetative index were selected from the mapped area and yield was calculated using NDVI (Normalized Difference Vegetation Index).

Farmonaut platform was used to map fields to create bounded regions (fields) as shown in Figure-2. On the dates of observations the sample fields were free from clouds and normal data was observed. Crop classification was done manually by ground truthing to ascertain the crop is standing in the field.

Maximum NDVI was used to calculate yields for the given fields which means peak vegetative growth rate. Peak vegetative growth helps to forecast yields more accurately.

Below are the observations of NDVI of the various fields. The maximum NDVI was reached on 4-Oct-2021 which was used to calculate yield. This approach is being used after going through a lot of available texts and final model was considered.

This model suggests direct correlation between grain yields and NDVI. This relationship was applied to all the fields to calculate yields.

NDVI started to rise after planting of crop in June continued to rise until 4-Oct-2021 making the data as best date for calculating yield. The NDVI started falling after 4-Oct-2021 and will fall until harvest. Best results of yield is obtained when the NDVI is maximum. In Figure 1 NDVI figures of three dates were taken and the date when the NDVI was maximum was considered.

NDVI showed the best correlation for the estimated yields. The yields ranged from 4.7 Tons/ha to 6.28 Tons/ha as shown in Figure 1 implying that most of the fields are having of long duration rice crop thereby generating higher NDVI. Also, the highest NDVI fields were selected meaning that most of the fields assessed is having long duration rice variety.

 Figure-1

Farmer

Area ( sq. m.)

24-09-2021

04-10-2021

09-10-2021

Estimated Yield (Tons/ha)

Field-1

32600

0.6

0.63

0.54

4.70

Field-2

9000

0.63

0.64

0.56

4.90

Field-3

12000

0.62

0.69

0.58

6.03

Field-4

3800

0.62

0.7

0.6

6.28

Field-5

22300

0.65

0.7

0.43

6.28

Field-6

5600

0.64

0.7

0.48

6.28

Field-7

5300

0.63

0.68

0.43

5.78

Field-8

4200

0.65

0.7

0.55

6.28

Field-9

6300

0.51

0.7

0.54

6.28

Field-10

12000

0.62

0.69

0.51

6.03

Results:

Our analysis of prediction of average yield was reported at 5.88 tons/ha which is in line with yield reported by Krishi Vigyan Kendra- Saharsa(ICAR) of 5-6 tons/ha for long duration crops. Our analysis show that the rice field used for yield prediction is mostly of long duration. Also, the prime reason of higher yield prediction was due to selection of fields which are producing highest NDVI skewing the data towards higher average yield. Which means the fields selected in our study is in upper quartile of yield implying long duration rice variety.

Data from Krishi Vigyan Kendra (KVK-Saharsa) showed that yields range between 5-6 tons/ha for long duration crop of 150-155 days (MTU 7029, Rajendra Masuri, Sabaur Shree, Sabaur Sampann) which will be harvested in November. For short duration rice crop of 90-100 days (Prabhat, Rajendra Bhagwati, Sabaur Surabhi etc) show mean yield of 3 tons/ha and it is harvested from mid-October. Also, yields in Saharsa is lower as it is situated on flood belts and around 80% of field is effected by water logging leading to lower yields compared to other districts. The above mentioned yields can vary depending upon weather before harvest as the crop is still standing while making the report. If conducive condition prevail then the above yields can be achieved.

The researches done in the area of yield forecasting of field crops by remote sensing has demonstrated good results. With the help of new sensors and indexes, researchers can calculate yields with less errors in future. Also, data by ground truthing will benefit the yield forecasting.

We will keep posting about any such informative information on to our blogs, to help as many people as possible. Farmonaut is built upon a vision to bridge the technological gap between farmers and strives to bring state-of-the-art technologies in the hands of each and every farmer. For any queries/suggestions, please contact us at support@farmonaut.com.

We have some more interesting articles coming up soon. Stay tuned!

Wait!!

Before that…

Follow us at:

Facebook: https://facebook.com/farmonaut

Instagram: https://instagram.com/farmonaut

Twitter: https://twitter.com/farmonaut

LinkedIn: https://www.linkedin.com/company/farmonaut/

Pinterest: https://in.pinterest.com/farmonaut/

Tumblr: https://farmonaut.tumblr.com/

Youtube: https://www.youtube.com/channel/UCYWOOPPKATLgh4L6YRlYFOQ

AppLink: https://play.google.com/store/apps/details?id=com.farmonaut.android

Website: https://farmonaut.com

Satellite Imagery: https://farmonaut.com/satellite-imagery

Satellite Imagery Samples: https://farmonaut.com/satellite-imagery-samples

 

 

Farmonaut Wheat And Paddy Yield Estimation

1. Wheat Yield (Saharsa Region Rabi 2020-2021)

During the Rabi season 2020-21, Farmonaut performed yield estimation of wheat in Saharsa district of Bihar using its remote sensing data and dedicated algorithms with several vegetation indices in consideration to create meaningful data and also by analyzing previous years data sets. 

The data generated and yield calculated was around 3.7 tonnes/hectare. However, after collecting the ground data and correlating with our estimated yield, we have noticed a deviation of up to 15% at some location. The mean yield achieved in the area was 4.4 tonnes/hectare as compared to our estimated 3.7 tonnes/hectare. 

By conducting such study purpose program, we, at farmonaut will improve and will come up with much better results in coming seasons.

2. Paddy Yield (Uttar Pradesh Region Kharif 2020-2021)

We conducted yield estimation program in Uttar Pradesh for paddy in kharif season 2020, for our research purpose, using various vegetation indices for every stage of crop to depict its characteristic throughout the cycle. 

Yield estimation is dependent on vegetative indices values which indicates the optimum time to harvest the crop to get maximum output from farms by checking biomass content. After going through the data of previous years and creating correlations, we used those algorithms and implemented them on the monitored fields and farms and our findings were quite close to the ground data with accuracy of more than 90% in results. 

 

We will continue our research work further to other crops too and will keep on posting our findings as well.

 

We will keep posting about any such informative information on to our blogs, to help as many people as possible. Farmonaut is built upon a vision to bridge the technological gap between farmers and strives to bring state-of-the-art technologies in the hands of each and every farmer. For any queries/suggestions, please contact us at support@farmonaut.com.

We have some more interesting articles coming up soon. Stay tuned!

Wait!!

Before that…

Follow us at:

Facebook: https://facebook.com/farmonaut

Instagram: https://instagram.com/farmonaut

Twitter: https://twitter.com/farmonaut

LinkedIn: https://www.linkedin.com/company/farmonaut/

Pinterest: https://in.pinterest.com/farmonaut/

Tumblr: https://farmonaut.tumblr.com/

Youtube: https://www.youtube.com/channel/UCYWOOPPKATLgh4L6YRlYFOQ

AppLink: https://play.google.com/store/apps/details?id=com.farmonaut.android

Website: https://farmonaut.com

Satellite Imagery: https://farmonaut.com/satellite-imagery

Satellite Imagery Samples: https://farmonaut.com/satellite-imagery-samples

 

 

Every time the satellite crosses location of the selected field, Farmonaut’s Satellite Based Crop Health Monitoring System generates field results as well as user downloadable reports as well. These user downloadable reports can be used for offline purposes when the user is not connected to the internet or wishes to share the field data with the on-field team. These auto-generated reports consist of the following information:

1. Weather Statistics on the Imagery Capture Date (Weather Station, Temperature (minimum and maximum), Pressure, Humidity, Wind Speed, Wind Direction, Cloud Cover)
2. Weather Graphs
3. Weather Forecast (Next 7 Days)
4. Index Data for the satellite captured date
5. Satellite Captured Images
6. Time series trend of the indices
7. Scientific background of the indices
8. Field area in different health zone for each index

The app is available on Google Play Store, Apple App Store as well as a Web App on our website. Happy Farming!

#farming #organicfarming #crops #urbanfarming #fieldscouting #remotesensing #greentech #smartfarming #precisionagriculture #agro #agrotech #farm #agritech #vegetables #agriculture #foodsecurity #technology #satellite #vegetation #india #gis

Introducing ROBUST POLYGON MANAGEMENT SYSTEM with the Farmonaut Web App. While monitoring a big area for crop health and water stress, a user may have to submit hundreds and thousands of polygons within a same master field to facilitate better data insight. To ensure a better accessibility for these large number of polygons within a field, farmers can now see a full searchable list of polygons on the interface itself as well as can provide a customized name for each and every polygon as well. By doing this, users can easily identify any specific polygon and analyze data for their ground level decision making.

Happy Farming!

#farming #organicfarming #crops #urbanfarming #fieldscouting #remotesensing #greentech #smartfarming #precisionagriculture #farm #agritech #agriculture #foodsecurity #technology #satellite #vegetation #india #gis #webapp #newfeature #organicmatter

While Monitoring the farms, it is essential to observe how different parts of the field have shown growth changes through time to make better on-field decisions. This can be done through Farmonaut’s Web App by comparing two satellite images simultaneously. You can select any two dates of satellite visits and compare results side by side on the map of the Farmonaut web app itself. Try this out if you haven’t yet.
Happy Farming!
#webapp #newfeature #organicmatter #farming #organicfarming #crops #urbanfarming #fieldscouting #remotesensing #greentech #smartfarming #precisionagriculture #agro #agrotech #farm #agritech #vegetables #agriculture #foodsecurity #technology #greentech #satellite #vegetation #india #gis #soil #soilhealth #soc

 

In 2016, fertilizer consumption for India was 165.8 kilograms per hectare. Fertilizer consumption of India increased from 100.3 kilograms per hectare in 2002 to 165.8 kilograms per hectare in 2016 growing at an average annual rate of 3.81 %.
The chemical price can vary from 250 rupees to 2000 rupees per kg depending upon the specific chemical being used. So on an average an Indian farmer spends between 41500 to 332000 rupees per year on each hectare of arable land.
Farmonaut identifies those areas of land where the crop growth is not normal. Farmer can apply fertilizers, chemicals, insecticides, pesticides, plant growth regulators etc. only in
those areas where the crop growth is not normal. By using
remote sensing results provided by Farmonaut, a farmer can save at least 30% on chemical consumption per year.
So for every one hectare of land, farmer can save at least between 12000 (~ $160) and 95000 (~ $1300) rupees per year.

The app is available on Google Play Store, Apple App Store as well as a Web App! Happy Farming!

#farming #organicfarming #crops #urbanfarming #fieldscouting #remotesensing #greentech #smartfarming #precisionagriculture #agro #agrotech #farm #agritech #vegetables #agriculture #foodsecurity #technology #greentech #satellite #vegetation #india #gis

PrecisionAg101 Post #4 : These posts are meant to make farmers aware of the basics of precision agriculture and how to interpret various satellite data provided by us.

The field image attached below is of the farmer Paulo o (Ponta Pora – State of Mato Grosso do Sul, 79900-000, Brazil), (Field Area: 47 Hectares). The image displayed on the map is NDRE (Normalized Difference Red Edge) captured by the satellite. NDRE images are used to quantify crop health when the crop is in the later stage of growth. NDVI index is not ideal for the crops in their later stage of growth because in grasses, cereal crops, permanent crops and in certain row crops which are in their later growth stages, chlorophyll content reaches a point at which NDVI reaches a maximum value of 1.0 and hence saturates. Hence, any crop health issue is hard to detect with NDVI until any such problem becomes strong enough to reduce the NDVI value below 1.0. This may happen at a point at which damage has already occurred. By substituting NDVI’s red band with NDRE’s red edge band we can mitigate this issue of saturation discussed above. So, in conclusion, if the crops of observation are permanent or dense, you should use NDRE right away. The colors used to quantify this information is very easy to interpret.

Dark Green/ Green: Crop is very healthy
Yellow: Crop needs attention
Red: Barren land

To cross-verify these results farmers can simply open GPS on their smartphones and can navigate through the field using this image.

By using satellite data provided by us, farmers can:
1. Reduce Chemical/Fertilizer consumption by applying them only in the locations where crop
health is not good.
2. Reduce Labour costs by directing the labours only in those field areas where crop health is
critical.
3. Reduce irrigation water wastage by applying proper irrigation only in those locations where
plant water stress is low.
4. Increase overall yield.

The system is available for use on android, iOS as well as web.

Happy Farming!

#farming #organicfarming #crops #urbanfarming #ndre #rededge #crophealth #fieldscouting #remotesensing #consultant #agriconsultant #greentech #smartfarming #precisionagriculture #farm

PrecisionAg101 Post #3 : These posts are meant to make farmers aware of the basics of precision agriculture and how to interpret various satellite data provided by us.

The field image attached below is of the farmer Tafuma Fundira (Masvingo, Zimbabwe), (Field Area: 2 Hectares). The image displayed on the map is ETCI (Enhanced True Color Image) on the left and VARI (Visible Atmospherically Resistant Index) image on the right. ETCI stands for Enhanced True Color Image. It is basically a TCI image processed by our own systems to enhance the land features which were not so explicitly visible in the raw TCI Image. VARI stands for Visible Atmospherically Resistant Index. VARI is minimally resistant to atmospheric effects, allowing vegetation to be estimated in a wide variety of environment. Hence, it is ideally recommended to be used for farm level decision making if TCI and ETCI images show visible atmospheric distortion such as mild clouds or haze above the field. The colors used to quantify this information is very easy to interpret.
Dark Green/ Green: Crop is very healthy
Yellow: Crop needs attention
Red: Barren land
In the posted image, as we can see, the ETCI image seems to be distorted due to haze and clouds. In such cases vegetation indices like NDVI will not give correct observations. Thus, VARI is used in such cases. As we can see through the VARI image, a majority of the field is growing pretty well, with some barren regions shown in red. To cross-verify these results farmers can simply open GPS on their smartphones and can navigate through the field using this image.

By using satellite data provided by us, farmers can:
1. Reduce Chemical/Fertilizer consumption by applying them only in the locations where crop health is not good.
2. Reduce Labour costs by directing the labours only in those field areas where crop health is critical.
3. Reduce irrigation water wastage by applying proper irrigation only in those locations where plant water stress is low.
4. Increase overall yield.

The system is available for use on android, iOS as well as web.

Happy Farming!
#farming #organicfarming #crops #urbanfarming #vari #crophealth #fieldscouting #remotesensing

PrecisionAg101 Post #2 : These posts are meant to make farmers aware of the basics of precision agriculture and how to interpret various satellite data provided by us.

The field image attached below is of the farmer Gullapalli Sujatha (Viswamatha farms, Andhra Pradesh, one of the pioneers in Natural Farming in India), (Field Area: 26 Hectares). The image displayed on the map is NDWI (Normalized Difference Water Index) captured by the satellite. NDWI images are used to quantify water stress in the vegetation in a field. NDWI index can help us control irrigation, significantly improving agriculture, especially in areas where meeting the need for water is difficult. The colors used to quantify this information is very easy to interpret.

Dark Green/ Green: water stress is good
Yellow: irrigation may need attention
Red: Barren land/ no vegetation

In the posted image, as we can see, the top portion of the field shows pretty good water stress in the vegetation, whereas the remaining field is in the yellowish or red region. This indicates that the farmer needs to pay attention to irrigation in these highlighted regions. To cross-verify these results farmers can simply open GPS on their smartphones and can navigate through the field using this image.

By using satellite data provided by us, farmers can:
1. Reduce Chemical/Fertilizer consumption by applying them only in the locations where crop
health is not good.
2. Reduce Labour costs by directing the labours only in those field areas where crop health is
critical.
3. Reduce irrigation water wastage by applying proper irrigation only in those locations where
plant water stress is low.
4. Increase overall yield.

The system is available for use on android, iOS as well as web.

Happy Farming!
#farming #organicfarming #crops #urbanfarming #ndwi #waterstress #fieldscouting #remotesensing #consultant #agriconsultant #greentech #smartfarming #precisionagriculture #farm #agritech #agriculture #foodsecurity #technology #satellite #vegetation #india #gis #waterstress #advisor #cropyield